© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4371
    Prev
    Next
    INDEX
    Explanations

    places and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     famiglia
    0.35
     عالم
    0.34
     della
    0.31
     اړه
    0.31
     جامعه
    0.31
     comunidade
    0.31
    .
    0.31
     omgeving
    0.31
     نړۍ
    0.30
     của
    0.30
    POSITIVE LOGITS
    ז
    0.33
    гана
    0.33
     которую
    0.32
    а
    0.32
     श्रीमती
    0.32
    ﹐
    0.32
    ጴ
    0.31
     י
    0.31
     које
    0.31
     promissory
    0.31
    Activations Density 0.333%

    No Known Activations