© 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. 128746
    Prev
    Next
    INDEX
    Explanations

    worked on or worked with

    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
    e
    -3.50
    𓐍
    -3.16
    u
    -3.05
    tividade
    -2.78
    ৹
    -2.77
    苌
    -2.69
    gencias
    -2.63
    ৪
    -2.61
    thenburg
    -2.59
    琿
    -2.45
    POSITIVE LOGITS
    '
    4.03
    .
    3.06
    "
    2.92
    ness
    2.61
    стреча
    2.55
    Apparently
    2.45
    новь
    2.44
    [
    2.42
    месте
    2.42
    乆
    2.41
    Activations Density 0.013%

    No Known Activations