© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8345
    Prev
    Next
    INDEX
    Explanations

    automotive applications and systems

    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
    ل
    2.09
    ي
    1.82
    الله
    1.77
    い
    1.75
    ᕆ
    1.74
    از
    1.71
    من
    1.67
    nesota
    1.67
     pandemi
    1.66
    V
    1.66
    POSITIVE LOGITS
    та
    2.53
    ak
    2.14
    차가
    1.91
    asjon
    1.63
     dioses
    1.57
    ahid
    1.49
    SAFE
    1.46
     prezzi
    1.46
    seeds
    1.43
    र्यंत
    1.43
    Activations Density 0.044%

    No Known Activations