© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    # followed by topic

    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
    માં
    2.09
    č
    1.88
    ä
    1.84
    ב
    1.77
    me
    1.75
    lan
    1.66
     비롯
    1.61
    le
    1.60
    }
    1.57
    #
    1.55
    POSITIVE LOGITS
     noqa
    2.03
     lieve
    1.84
     assailant
    1.78
    ಯ್ಯ
    1.77
    MeToo
    1.72
    ਾ
    1.72
     canoes
    1.70
     initiating
    1.69
     hallucinations
    1.67
     गौरतलब
    1.66
    Activations Density 0.221%

    No Known Activations