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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239095
    Prev
    Next
    INDEX
    Explanations

    our communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    -
    0.45
    I
    0.44
     Permission
    0.44
    EL
    0.42
    </strong>
    0.41
    OP
    0.41
    BrN
    0.41
    DON
    0.40
    قاب
    0.40
     Disturb
    0.39
    POSITIVE LOGITS
     ට
    0.61
     πλα
    0.57
     구
    0.56
     வங்க
    0.56
    家の
    0.55
    countery
    0.54
     politique
    0.52
     亻
    0.52
     Акысыз
    0.51
     கு
    0.51
    Activations Density 0.000%

    No Known Activations