© 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. 34-GEMMASCOPE-RES-131K
    4. 110533
    Prev
    Next
    INDEX
    Explanations

    in the present study

    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_34/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
    TestResult
    -0.78
    Rape
    -0.76
    testdata
    -0.74
     cubre
    -0.74
    waffle
    -0.73
    season
    -0.73
    libur
    -0.73
    Annotated
    -0.71
    ₂)
    -0.71
    пыта
    -0.70
    POSITIVE LOGITS
     study
    6.44
     studies
    5.16
    study
    4.47
     Study
    4.09
    Study
    4.00
     estudio
    3.72
     STUDY
    3.64
     estudo
    3.59
    STUDY
    3.41
    studies
    3.25
    Activations Density 0.445%

    No Known Activations