© 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. 255582
    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
    ii
    0.58
    iances
    0.54
    ry
    0.53
    ady
    0.50
    nl
    0.50
    adi
    0.50
    n
    0.47
    ned
    0.46
    ments
    0.46
    ât
    0.46
    POSITIVE LOGITS
     infrac
    0.57
     EDGE
    0.53
     gota
    0.50
     infringement
    0.48
     Liebe
    0.48
    펩
    0.48
    곽
    0.48
     частина
    0.46
     impulsar
    0.46
    ።
    0.46
    Activations Density 0.000%

    No Known Activations