© 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. 129548
    Prev
    Next
    INDEX
    Explanations

    programming function calls

    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
    It
    -3.45
    They
    -3.02
    This
    -2.98
    The
    -2.78
    With
    -2.77
    Its
    -2.77
    An
    -2.66
    婞
    -2.63
    Their
    -2.63
    These
    -2.61
    POSITIVE LOGITS
    jaqueta
    2.67
    罽
    2.59
    筴
    2.55
    韡
    2.55
    欤
    2.50
    萑
    2.50
     añade
    2.48
     trabaja
    2.45
    稣
    2.42
    呓
    2.42
    Activations Density 0.002%

    No Known Activations