© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 302
    Prev
    Next
    INDEX
    Explanations

    function or outcome description

    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
     on
    -1.56
    RTHOOK
    -1.47
    izop
    -1.45
    چ
    -1.34
    }^{
    -1.31
    stateProvider
    -1.30
    "..."
    -1.27
     such
    -1.27
    vanju
    -1.27
    //{
    -1.25
    POSITIVE LOGITS
     ettei
    1.55
    </h1>
    1.53
     élas
    1.48
    k
    1.42
     rempliss
    1.38
     التي
    1.35
    6
    1.33
     angebra
    1.31
     élastique
    1.31
     Nachdem
    1.30
    Activations Density 0.058%

    No Known Activations