© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11509
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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_22/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
     asunto
    -1.08
     sqm
    -1.05
     vasto
    -1.01
    そのため
    -0.97
    sies
    -0.97
     hende
    -0.96
     își
    -0.96
     a
    -0.96
    ckeye
    -0.95
     !
    -0.94
    POSITIVE LOGITS
     bañ
    1.17
     betyr
    1.13
    デート
    1.13
     pieniądze
    1.09
    .
    1.09
     aéri
    1.08
    >(&
    1.06
     наконец
    1.03
    ところに
    1.02
     органі
    1.01
    Activations Density 0.000%

    No Known Activations