© 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. 22-GEMMASCOPE-RES-131K
    7. 26463
    Prev
    Next
    INDEX
    Explanations

    security attributes

    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_22/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
     knew
    -1.23
     know
    -1.13
     wspar
    -1.07
     ciclismo
    -1.04
     tył
    -1.02
     千葉
    -1.02
     {};
    -1.02
     られ
    -1.00
     xăm
    -1.00
     knows
    -0.99
    POSITIVE LOGITS
     “
    1.09
    </strong>
    1.09
     °
    1.08
     zb
    1.03
     ,
    1.02
    still
    1.02
     الجهاز
    1.02
     ^
    1.02
    uride
    1.00
    Embedded
    0.99
    Activations Density 0.007%

    No Known Activations