© 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. 8673
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "__main__":

    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
    ط
    0.97
    ﻣ
    0.91
     modifica
    0.80
    で
    0.80
     construye
    0.79
     grabado
    0.78
     dels
    0.77
    шенные
    0.77
     وحتى
    0.77
     وكل
    0.77
    POSITIVE LOGITS
    ic
    1.16
    لی
    0.99
    lere
    0.97
    <0x80>
    0.95
    ase
    0.89
    los
    0.89
    lah
    0.87
    pas
    0.84
    sti
    0.80
    lm
    0.79
    Activations Density 0.002%

    No Known Activations