© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 30871
    Prev
    Next
    INDEX
    Explanations

    specific nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pidió
    1.15
    鐢
    1.09
     corretamente
    1.05
     zahlreiche
    1.03
     bezieht
    1.03
    有一定的
    1.02
     blieb
    1.02
    ……….
    1.01
     erreichte
    1.01
     connaît
    1.00
    POSITIVE LOGITS
    s
    1.75
    san
    1.55
    ς
    1.47
    sa
    1.46
    r
    1.42
    sion
    1.35
    sand
    1.33
    suit
    1.29
     I
    1.27
    selves
    1.27
    Activations Density 0.000%

    No Known Activations