© 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. 128357
    Prev
    Next
    INDEX
    Explanations

    asserting knowledge

    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
     a
    -1.47
    ’,
    -1.36
    providedIn
    -1.31
     famosa
    -1.26
     mystérie
    -1.24
    </i>
    -1.22
    ’.
    -1.20
     abenço
    -1.20
     gracios
    -1.18
    trá
    -1.16
    POSITIVE LOGITS
     nothing
    1.44
    無論
    1.35
     know
    1.35
     twar
    1.34
     nobody
    1.30
     pouze
    1.27
     neither
    1.26
     fact
    1.25
     that
    1.25
     capucha
    1.24
    Activations Density 0.019%

    No Known Activations