© 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. 96437
    Prev
    Next
    INDEX
    Explanations

    policy or politics

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

    explanations of why choices are made

    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
    screenshot
    0.49
    ୍ୟ
    0.48
    Acetic
    0.47
    noof
    0.47
    inburgh
    0.46
    msk
    0.46
    ଢ
    0.45
    total
    0.44
     क्षार
    0.44
    𝘩
    0.44
    POSITIVE LOGITS
     political
    0.54
     Tard
    0.46
     Geno
    0.46
     expl
    0.45
     Raim
    0.45
     políticas
    0.45
     sign
    0.44
     politique
    0.43
     radar
    0.42
     splendor
    0.42
    Activations Density 0.003%

    No Known Activations