© 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. 40035
    Prev
    Next
    INDEX
    Explanations

    "within"

    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
     we
    -1.52
     Another
    -1.48
     that
    -1.47
     Then
    -1.46
    Another
    -1.36
    Someone
    -1.36
    Personally
    -1.34
    Use
    -1.28
     use
    -1.28
     which
    -1.28
    POSITIVE LOGITS
    ⽼
    1.63
     kunde
    1.46
     controladores
    1.32
     Мария
    1.30
    yyah
    1.29
     Евгений
    1.28
    Ꮔ
    1.27
     bocetos
    1.27
    !’
    1.25
     teaspoon
    1.24
    Activations Density 0.029%

    No Known Activations