© 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. 237218
    Prev
    Next
    INDEX
    Explanations

    completion and restoration

    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
    ل
    0.55
    „
    0.51
    دو
    0.49
    ONG
    0.49
    م
    0.48
    Seller
    0.48
    Replacing
    0.47
    س
    0.47
     criar
    0.46
    Create
    0.46
    POSITIVE LOGITS
    tense
    0.52
    paration
    0.49
     Нико
    0.48
     NH
    0.47
     XK
    0.47
     நடை
    0.47
     GI
    0.44
    plement
    0.44
     완료
    0.44
     Gymnasium
    0.43
    Activations Density 0.000%

    No Known Activations