© 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. 102664
    Prev
    Next
    INDEX
    Explanations

    life easier

    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
     that
    -1.60
    ÑOS
    -1.40
    らしいです
    -1.38
    qwerty
    -1.35
    続きます
    -1.33
    ेशा
    -1.29
     Cia
    -1.26
    闐
    -1.23
     prachtige
    -1.22
     reeks
    -1.20
    POSITIVE LOGITS
    If
    1.85
    }
    1.79
    It
    1.73
    }\
    1.67
     =
    1.65
    >
    1.65
    ↵↵
    1.62
    Where
    1.60
    if
    1.57
     {
    1.54
    Activations Density 0.032%

    No Known Activations