© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8060
    Prev
    Next
    INDEX
    Explanations

    Russian prefixes and word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    основа, čast, создание, волосы

    np_acts-logits-general · gemini-2.5-flash-lite

    words and phrases in non-English languages, particularly Russian and other Cyrillic text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @sripadkarne

    text in Cyrillic script, particularly Russian language content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @sripadkarne

    period

    np_max-act · claude-4-5-sonnetTriggered by @sripadkarne

    period

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    淔
    0.49
    किस्तानी
    0.48
    ٽ
    0.47
     direita
    0.47
     هڪ
    0.47
    ڎ
    0.46
     ٻ
    0.46
    direita
    0.45
    chiha
    0.45
    㚅
    0.45
    POSITIVE LOGITS
     Про
    0.97
     По
    0.95
     При
    0.95
     Основ
    0.93
     В
    0.91
     П
    0.90
     На
    0.89
     Раз
    0.88
     За
    0.88
     Пре
    0.87
    Activations Density 0.009%

    No Known Activations