© 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. 68284
    Prev
    Next
    INDEX
    Explanations

    Frankie and code comments

    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
     Reſ
    -2.80
    ارتمان
    -2.56
    ſſen
    -2.50
    悭
    -2.50
     péro
    -2.47
    𓆏
    -2.45
     Gegensatz
    -2.39
    蟶
    -2.38
    蜑
    -2.38
    rungsseite
    -2.34
    POSITIVE LOGITS
    \
    2.98
    of
    2.97
    ."
    2.89
     WHILE
    2.55
    _
    2.48
     There
    2.48
     While
    2.42
    完美
    2.23
     của
    2.22
    .[
    2.22
    Activations Density 0.009%

    No Known Activations