© 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. 111231
    Prev
    Next
    INDEX
    Explanations

    specific details or definitions

    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
    ﺔ
    0.44
     flirting
    0.43
     multiplications
    0.43
    iguë
    0.43
    jecha
    0.43
     robbing
    0.43
    BagConstraints
    0.42
     lamin
    0.42
    crayon
    0.41
     provoking
    0.41
    POSITIVE LOGITS
    ใน
    0.47
     espectacular
    0.45
     São
    0.44
     proteger
    0.44
    El
    0.44
     অ
    0.44
    Se
    0.44
    بي
    0.44
    boldsymbol
    0.44
    ului
    0.43
    Activations Density 0.007%

    No Known Activations