© 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. 43881
    Prev
    Next
    INDEX
    Explanations

    decision making or responsibility

    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
     and
    -1.14
     yyb
    -1.13
    biť
    -1.08
    HideFlags
    -1.08
    сть
    -1.08
    })$.
    -1.07
    < 
    -1.06
    𞤢
    -1.05
     décennies
    -1.05
    wą
    -1.05
    POSITIVE LOGITS
     to
    1.48
    ates
    1.27
    Folgende
    1.23
     şun
    1.23
    小声
    1.19
     ответственность
    1.16
     responsibility
    1.13
    important
    1.13
     некоторы
    1.12
    tabla
    1.11
    Activations Density 0.053%

    No Known Activations