© 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. 234162
    Prev
    Next
    INDEX
    Explanations

    less honest, instead of

    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
    ght
    0.50
    땃
    0.49
    udi
    0.49
    ast
    0.48
    abi
    0.48
     Κο
    0.47
    ante
    0.47
    grave
    0.46
    wol
    0.46
    ind
    0.46
    POSITIVE LOGITS
    こちらは
    0.51
    ط
    0.50
    传入
    0.49
     normality
    0.47
    店舗
    0.46
    ب
    0.45
    原因
    0.45
     deff
    0.44
    zellen
    0.44
    モダン
    0.44
    Activations Density 0.000%

    No Known Activations