© 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. 141
    Prev
    Next
    INDEX
    Explanations

    the followed by common 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
    .
    1.30
    ANCE
    1.05
    /
    1.02
    ierten
    0.95
     Whey
    0.93
    kannya
    0.88
    دة
    0.87
    ה
    0.87
    ius
    0.86
    .}$
    0.85
    POSITIVE LOGITS
    щий
    1.11
    ্কার
    1.10
    жды
    1.08
     تاہم
    1.05
    暠
    1.05
    não
    1.04
    ług
    1.03
    щие
    1.02
    тной
    1.00
    і
    1.00
    Activations Density 0.015%

    No Known Activations