© 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. 99393
    Prev
    Next
    INDEX
    Explanations

    programming task definitions

    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
    雠
    -3.22
    酲
    -3.11
     Conſ
    -3.09
     ſmall
    -3.08
    饹
    -2.86
    ︲
    -2.83
    䊐
    -2.80
    蕺
    -2.78
     Perſ
    -2.77
    旨在
    -2.77
    POSITIVE LOGITS
    u
    3.38
    b
    3.00
    P
    2.97
    ll
    2.92
    ta
    2.89
    er
    2.89
    S
    2.78
    L
    2.72
    do
    2.64
     As
    2.64
    Activations Density 0.013%

    No Known Activations