© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98998
    Prev
    Next
    INDEX
    Explanations

    just might

    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
     другими
    -1.63
    hancing
    -1.54
     tomaron
    -1.52
    䊐
    -1.48
     sostu
    -1.48
    ologic
    -1.43
    colgante
    -1.43
    ␻
    -1.42
    犼
    -1.39
    CELONA
    -1.35
    POSITIVE LOGITS
     also
    1.69
    nehå
    1.51
    cję
    1.40
    AZIONE
    1.37
    だけでも
    1.34
    ALREADY
    1.34
    onesi
    1.33
    ulico
    1.32
    ,))
    1.32
     our
    1.32
    Activations Density 0.011%

    No Known Activations