© 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. 69806
    Prev
    Next
    INDEX
    Explanations

    amounts of

    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
    蟊
    -2.86
    ſam
    -2.83
    鱚
    -2.58
     ilha
    -2.56
    山的
    -2.55
    鯪
    -2.55
    😚
    -2.52
    ;
    -2.52
     hamil
    -2.47
    ;</
    -2.45
    POSITIVE LOGITS
    </em>
    3.11
     amounts
    2.98
    ↵↵
    2.84
    Initially
    2.69
     Primarily
    2.67
     Presumably
    2.66
     Commonly
    2.64
     Literally
    2.63
     Effectively
    2.58
     Importantly
    2.55
    Activations Density 0.008%

    No Known Activations