© 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. 68111
    Prev
    Next
    INDEX
    Explanations

    your assets

    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
    Kemudian
    -1.68
    Namun
    -1.59
    )}$.
    -1.45
     etre
    -1.44
     eure
    -1.42
     малы
    -1.40
    Mereka
    -1.38
    Tidak
    -1.38
    达到了
    -1.38
     используется
    -1.35
    POSITIVE LOGITS
     a
    2.03
     in
    1.86
    _
    1.82
     with
    1.62
    </strong>
    1.59
    cloudf
    1.59
    salomon
    1.59
     its
    1.56
    ктей
    1.50
    ípio
    1.46
    Activations Density 0.033%

    No Known Activations