© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11455
    Prev
    Next
    INDEX
    Explanations

    flags, registers, and logic conditions

    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
    0.78
    6
    0.70
     /
    0.70
    inen
    0.67
    automation
    0.66
     Satisfaction
    0.66
    get
    0.66
    supplement
    0.66
    的女
    0.65
    4
    0.65
    POSITIVE LOGITS
     emulsions
    0.93
    नून
    0.81
     corrientes
    0.81
     руху
    0.79
    ánea
    0.79
    ृत्व
    0.77
    बैक
    0.77
    ジネス
    0.75
    リューム
    0.75
    甃
    0.75
    Activations Density 0.000%

    No Known Activations