© 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. 173473
    Prev
    Next
    INDEX
    Explanations

    car title loans

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

    email only

    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
    ಧ್ಯ
    0.51
     ზ
    0.50
     identique
    0.50
    擔任
    0.49
    朝鮮
    0.49
    іль
    0.47
    接觸
    0.47
    ედერ
    0.46
    譚
    0.46
    教師
    0.46
    POSITIVE LOGITS
    un
    0.53
    Rem
    0.50
    );
    0.47
    ui
    0.46
     et
    0.46
    uy
    0.45
     cualquier
    0.45
    any
    0.44
     sap
    0.44
     l
    0.44
    Activations Density 0.000%

    No Known Activations