© 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. 20656
    Prev
    Next
    INDEX
    Explanations

    technical followed by specifics

    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
     The
    -2.66
    '
    -2.63
     今
    -2.50
     Which
    -2.45
     présentent
    -2.25
    ができる
    -2.23
     
    -2.19
     concepción
    -2.16
     replete
    -2.16
     BEFORE
    -2.09
    POSITIVE LOGITS
    S
    3.13
    U
    3.05
    D
    3.03
    蚴
    3.00
    .
    2.98
     inglese
    2.95
    B
    2.92
    C
    2.92
    K
    2.92
    ﹑
    2.91
    Activations Density 0.007%

    No Known Activations