© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9996
    Prev
    Next
    INDEX
    Explanations

    political figures and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -1.38
    ceedings
    -1.28
    Legături
    -1.16
    erobic
    -1.16
     reckless
    -1.14
     those
    -1.14
     excessively
    -1.13
     February
    -1.12
    扁平
    -1.09
    称号
    -1.09
    POSITIVE LOGITS
     différents
    1.18
     unlike
    1.13
    icles
    1.09
    whether
    1.06
     in
    1.04
     plusieurs
    1.03
     away
    1.01
    悄悄
    1.01
    despite
    1.00
    unlike
    0.99
    Activations Density 0.108%

    No Known Activations