© 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. 22-GEMMASCOPE-RES-131K
    7. 33933
    Prev
    Next
    INDEX
    Explanations

    predicted probabilities or values

    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_22/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
    AM
    -1.07
    AC
    -1.05
     he
    -1.03
    },
    -0.99
    <em>
    -0.99
    </h3>
    -0.96
    ‘
    -0.95
    /*
    -0.95
    */
    -0.94
     podróż
    -0.94
    POSITIVE LOGITS
    ristorante
    1.35
    吶
    1.23
     хоче
    1.23
     noemen
    1.16
    Materiale
    1.14
    というわけで
    1.14
    樣子
    1.12
    <0xA3>
    1.12
     Bedürfnisse
    1.11
    灕
    1.10
    Activations Density 0.003%

    No Known Activations