© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 37488
    Prev
    Next
    INDEX
    Explanations

    as a way

    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
     ومن
    0.98
    ेंसी
    0.89
    ن
    0.88
    нение
    0.87
    igit
    0.86
    atically
    0.86
    ่อ
    0.85
    ências
    0.85
    icación
    0.84
     күзгү
    0.84
    POSITIVE LOGITS
    S
    1.13
    U
    1.12
    M
    1.02
    I
    1.01
    K
    1.01
    Ş
    0.96
    D
    0.95
    B
    0.95
     usual
    0.95
    Napoleon
    0.94
    Activations Density 0.058%

    No Known Activations