© 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. 4652
    Prev
    Next
    INDEX
    Explanations

    pre- words

    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
    ari
    2.22
    arı
    2.06
    d
    1.98
    m
    1.95
    mout
    1.91
    mouth
    1.91
    ри
    1.90
    लिये
    1.88
    牒
    1.88
    t
    1.84
    POSITIVE LOGITS
     estatura
    1.99
    pped
    1.90
     Neuer
    1.88
    angleright
    1.77
     mortem
    1.77
    ップ
    1.73
     ومع
    1.71
    されて
    1.70
    しない
    1.67
    ท์
    1.67
    Activations Density 0.017%

    No Known Activations