© 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. 8847
    Prev
    Next
    INDEX
    Explanations

    frame manipulation

    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
    ot
    2.53
    ن
    2.50
    sa
    2.22
    да
    2.16
    스럽
    2.16
    رة
    2.08
    ड
    2.02
    스러운
    1.98
    ল
    1.95
    রা
    1.95
    POSITIVE LOGITS
    er
    2.23
    শনাল
    2.02
     سازی
    1.95
    e
    1.88
    )";
    1.85
    一共
    1.83
    erder
    1.83
    ય
    1.80
    ્સ
    1.79
    槭
    1.73
    Activations Density 0.055%

    No Known Activations