© 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. 110536
    Prev
    Next
    INDEX
    Explanations

    math and character representations

    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
     SWEET
    -0.73
    quam
    -0.69
     recess
    -0.69
     kern
    -0.69
     Voyages
    -0.68
     pope
    -0.68
     sanctions
    -0.68
    isc
    -0.66
     palab
    -0.66
     millet
    -0.66
    POSITIVE LOGITS
    CHR
    0.97
     Character
    0.85
     캐릭터
    0.82
     charismatic
    0.81
    ̜
    0.79
     character
    0.77
    roberto
    0.75
    Character
    0.74
     CHR
    0.73
    釧
    0.73
    Activations Density 0.111%

    No Known Activations