© 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. 387
    Prev
    Next
    INDEX
    Explanations

    break down

    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
    t
    1.25
    و
    0.90
    ו
    0.89
    はお
    0.86
    tio
    0.84
    M
    0.84
    er
    0.83
    Y
    0.82
    h
    0.81
    க
    0.81
    POSITIVE LOGITS
     canisters
    0.95
     microtubules
    0.87
     chickpeas
    0.86
     monolayers
    0.82
    ரத்தில்
    0.79
     Vestone
    0.79
    ষুধ
    0.78
    ные
    0.77
    ება
    0.77
     potentialities
    0.76
    Activations Density 0.360%

    No Known Activations