© 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. 41831
    Prev
    Next
    INDEX
    Explanations

    state government

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

    on either side

    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
     verantwort
    0.55
    تدائي
    0.54
    дея
    0.50
    目光
    0.49
     stärker
    0.49
    hæng
    0.49
     abhäng
    0.48
    妏
    0.48
    以及
    0.48
    ：
    0.48
    POSITIVE LOGITS
    jan
    0.49
    icity
    0.48
    agh
    0.44
    angels
    0.44
    getic
    0.43
    ...
    0.43
    Dict
    0.43
    encers
    0.43
    il
    0.42
    aje
    0.42
    Activations Density 0.000%

    No Known Activations