© 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. 260064
    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
     Sandia
    0.46
     Oficial
    0.46
     Szcz
    0.46
     Hernandez
    0.45
     Sund
    0.45
    *,
    0.44
     Nawaz
    0.44
     Gł
    0.44
     PRIOR
    0.44
     Serv
    0.43
    POSITIVE LOGITS
    வுகள்
    0.46
    etok
    0.45
    ফে
    0.45
    寜
    0.44
     voisines
    0.44
    метр
    0.44
    다고
    0.44
     vox
    0.44
    𝕦
    0.44
    افيه
    0.43
    Activations Density 0.001%

    No Known Activations