© 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. 24-GEMMASCOPE-2-RES-262K
    7. 3298
    Prev
    Next
    INDEX
    Explanations

    file paths

    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_24_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
    ₁,
    0.44
    ₂,
    0.44
     변화
    0.42
     Croce
    0.42
     diminishes
    0.41
     ToString
    0.41
     Conclusions
    0.41
     emphasises
    0.39
     Textiles
    0.39
    েন্টস
    0.38
    POSITIVE LOGITS
    new
    0.54
    d
    0.53
    n
    0.52
    g
    0.51
    x
    0.50
    data
    0.48
    r
    0.48
    server
    0.48
    my
    0.47
    app
    0.47
    Activations Density 0.049%

    No Known Activations