© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    variable z

    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
    ature
    2.03
    age
    1.97
    gmzy
    1.95
    り
    1.95
    서
    1.87
    ки
    1.86
    wdriver
    1.85
    io
    1.83
    iciency
    1.80
    śmy
    1.77
    POSITIVE LOGITS
    ्ड
    2.83
    क
    2.50
    влека
    2.41
    ру
    2.39
    UR
    2.33
    ин
    2.30
    ﻟ
    2.28
    ный
    2.27
    cómo
    2.22
    ﻧ
    2.20
    Activations Density 0.195%

    No Known Activations