© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40277
    Prev
    Next
    INDEX
    Explanations

    900 block of Desplaines Street

    np_acts-logits-general · gemini-2.5-flash-lite

    link between

    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
    荕
    0.53
    schule
    0.50
    URNIZ
    0.47
     khoản
    0.47
    szlig
    0.47
     desconoc
    0.46
    {\'
    0.46
    ইন
    0.46
     regenv
    0.46
    aderamente
    0.45
    POSITIVE LOGITS
     „
    0.49
     punch
    0.49
     contraction
    0.48
    變成
    0.47
     swaying
    0.47
     —
    0.46
     Ripp
    0.45
    Punch
    0.44
     fluttering
    0.44
     Punch
    0.44
    Activations Density 0.000%

    No Known Activations