© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43491
    Prev
    Next
    INDEX
    Explanations

    defined click, patient has, break above

    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
     zaten
    -1.55
    fasterxml
    -1.52
     zustand
    -1.45
     
    -1.41
    mejores
    -1.41
     already
    -1.38
     usual
    -1.38
     The
    -1.38
    你先
    -1.37
    ほん
    -1.36
    POSITIVE LOGITS
    chelles
    1.56
    Vendredi
    1.55
     as
    1.46
    Jeudi
    1.44
    llingwood
    1.41
     and
    1.38
     sibi
    1.38
    )");
    1.38
    foglio
    1.37
    𝚟
    1.34
    Activations Density 0.090%

    No Known Activations