© 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. 6677
    Prev
    Next
    INDEX
    Explanations

    negative aspects and cons

    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
    ี
    0.99
    ina
    0.89
    ни
    0.85
    ines
    0.81
    ih
    0.80
    il
    0.79
    ια
    0.79
    oned
    0.77
    ષા
    0.77
    mies
    0.76
    POSITIVE LOGITS
    🤮
    0.95
    </strong>
    0.79
    తర
    0.79
    😥
    0.79
     나머지
    0.77
    👿
    0.77
    🙅
    0.76
     Ви
    0.75
     vajj
    0.75
    😠
    0.75
    Activations Density 1.283%

    No Known Activations