© 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. 254846
    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
    The
    0.48
     Offices
    0.48
     The
    0.46
    г
    0.46
     Pre
    0.46
    फ
    0.46
    의
    0.45
     Painting
    0.45
     Personal
    0.44
     Presses
    0.44
    POSITIVE LOGITS
    apa
    0.52
     букмекерлик
    0.48
    cije
    0.47
    iyorum
    0.45
    Methylsulfanyl
    0.45
     口
    0.44
     জায়গায়
    0.44
     conducción
    0.43
    UNRELATED
    0.43
     সির
    0.43
    Activations Density 0.001%

    No Known Activations