© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110416
    Prev
    Next
    INDEX
    Explanations

    power and set operations

    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
    Purple
    -0.82
    Meanwhile
    -0.79
     Pullman
    -0.77
     Iman
    -0.74
     Gopal
    -0.73
     هن
    -0.71
    _<
    -0.71
    Еще
    -0.71
     Pantry
    -0.70
    Orange
    -0.69
    POSITIVE LOGITS
     power
    2.59
    power
    2.14
     Power
    2.03
    Power
    1.93
    POWER
    1.77
     POWER
    1.73
    パワー
    1.33
    setPower
    1.23
    幂
    1.23
     pow
    1.22
    Activations Density 0.020%

    No Known Activations