© 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. 255535
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ين
    1.19
    ל
    1.12
    ת
    1.04
    ва
    0.89
    კ
    0.88
    ل
    0.88
     opos
    0.84
    ر
    0.83
    رك
    0.82
    ס
    0.80
    POSITIVE LOGITS
    ?
    0.91
    1
    0.83
    !
    0.81
    h
    0.79
    城市
    0.76
    t
    0.75
    ong
    0.71
     I
    0.68
    <0x81>
    0.67
    <0x8D>
    0.67
    Activations Density 0.066%

    No Known Activations