© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100273
    Prev
    Next
    INDEX
    Explanations

    non-English words and usages

    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
     Можно
    0.49
     Existe
    0.48
     Boltzmann
    0.47
     GG
    0.45
    Bet
    0.44
     n
    0.42
     N
    0.42
     オレンジ
    0.42
     mentales
    0.42
    ్
    0.42
    POSITIVE LOGITS
    relationships
    0.46
     রজ
    0.43
    practices
    0.43
     đô
    0.42
    《
    0.40
    找到
    0.40
     poderosa
    0.40
    度
    0.40
     usadas
    0.39
    doch
    0.39
    Activations Density 0.001%

    No Known Activations