© 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. 260818
    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
     ぐらい
    0.60
     eccles
    0.58
     везе
    0.57
    ኦ
    0.56
     Rovio
    0.55
     सहयोग
    0.53
     condam
    0.53
     चर्च
    0.53
    リリース
    0.53
    ี่ยน
    0.52
    POSITIVE LOGITS
    ē
    0.46
    amas
    0.45
    ()];
    0.44
    最
    0.42
    jan
    0.42
    க்கொண்ட
    0.41
     />;
    0.41
    idoo
    0.41
    ے
    0.40
    ynia
    0.39
    Activations Density 0.000%

    No Known Activations