© 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. 61259
    Prev
    Next
    INDEX
    Explanations

    owners and entities

    np_acts-logits-general · gemini-2.5-flash-lite

    method, class, primary, loop, located

    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
    Erik
    0.51
    Brian
    0.49
    Descripcion
    0.47
    ர்வ
    0.47
    рою
    0.45
    ਤ
    0.45
    alas
    0.44
    测
    0.43
    export
    0.43
    axios
    0.42
    POSITIVE LOGITS
     väč
    0.54
     Shareholders
    0.54
     pemilik
    0.51
     వెంటనే
    0.50
     SHARE
    0.50
     Behör
    0.50
     أهل
    0.49
     Habsburg
    0.49
     Owned
    0.49
     PRESIDENT
    0.49
    Activations Density 0.000%

    No Known Activations