© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    analyze, handle, calculate

    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
    c
    1.25
    t
    1.23
    m
    1.14
    l
    1.13
    IN
    1.12
    و
    1.12
    ↵
    1.10
    g
    1.09
    d
    1.05
    ll
    0.98
    POSITIVE LOGITS
     dignitaries
    0.98
     Shee
    0.90
    🌜
    0.88
    ances
    0.86
    ♢
    0.84
    স্থানীয়
    0.84
    ान
    0.83
    াবাদী
    0.83
    技術
    0.82
    емые
    0.82
    Activations Density 2.043%

    No Known Activations