Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 190
    Prev
    Next
    INDEX
    Explanations

    action phrases like "traded blows" or "chase down"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    k
    1.23
    kette
    0.89
    ising
    0.87
    '
    0.85
     নিজেই
    0.80
    也许
    0.80
    kran
    0.79
    kosten
    0.78
    $
    0.78
    eless
    0.78
    POSITIVE LOGITS
     Въ
    1.02
     seguenti
    0.95
    IONES
    0.94
    皞
    0.92
     cuaderno
    0.84
     దీంతో
    0.83
     Nation
    0.82
     digitales
    0.82
     অপহরণকারীদের
    0.81
     т
    0.81
    Activations Density 0.000%

    No Known Activations