© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    blisters

    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
    ט
    1.89
    ა
    1.70
    я
    1.66
    ્સ
    1.63
    л
    1.59
    ен
    1.55
    ться
    1.53
    ียร์
    1.52
    られ
    1.52
    ب
    1.48
    POSITIVE LOGITS
    ing
    1.69
     iż
    1.53
    ש
    1.45
    oh
    1.44
    heroku
    1.36
     afar
    1.35
    ڈ
    1.34
    pann
    1.31
     ASSERT
    1.30
    ¿
    1.30
    Activations Density 0.006%

    No Known Activations