© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7702
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    /
    0.95
    Ons
    0.89
    '
    0.89
    ends
    0.80
     or
    0.78
    :
    0.78
     and
    0.76
     occurrences
    0.75
     obedience
    0.74
    uers
    0.73
    POSITIVE LOGITS
    ა
    1.13
    oretically
    1.08
    ский
    1.02
    9
    0.95
    ান
    0.93
     делает
    0.91
    ৯
    0.91
    ти
    0.90
    7
    0.90
    6
    0.88
    Activations Density 0.174%

    No Known Activations