© 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. 101233
    Prev
    Next
    INDEX
    Explanations

    gentle descriptions and actions

    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
    </strong>
    -2.41
    皷
    -2.41
     immense
    -2.30
    廛
    -2.17
     delegación
    -2.14
    锨
    -2.09
    le
    -2.09
     desse
    -2.08
    ৄ
    -2.08
    詎
    -2.06
    POSITIVE LOGITS
    There
    3.41
    These
    3.19
    This
    3.19
    Some
    3.06
    It
    3.05
    You
    2.95
    We
    2.92
    Although
    2.91
    Many
    2.80
    1
    2.80
    Activations Density 0.002%

    No Known Activations