© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    go first or go to

    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
    О
    2.27
    ח
    1.88
     weten
    1.84
    ற
    1.80
    ال
    1.78
     locali
    1.73
    ના
    1.71
    ת
    1.71
    д
    1.70
     essendo
    1.70
    POSITIVE LOGITS
    NING
    1.70
    تان
    1.64
    ल्डेन
    1.61
     parody
    1.60
    vät
    1.57
    quantile
    1.55
     COL
    1.54
     Compos
    1.52
    OOL
    1.52
    hyun
    1.52
    Activations Density 0.054%

    No Known Activations