© 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. 1598
    Prev
    Next
    INDEX
    Explanations

    actions that happened

    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
    పై
    0.90
     poderá
    0.80
     résult
    0.76
     teeming
    0.76
     deverá
    0.75
    ਾ
    0.75
     necesit
    0.75
     majd
    0.75
     crouching
    0.71
    ،
    0.71
    POSITIVE LOGITS
    s
    1.20
    ар
    0.96
    ت
    0.95
    ের
    0.95
    г
    0.93
    ों
    0.90
    एल
    0.90
    ス
    0.89
    ant
    0.88
    ter
    0.87
    Activations Density 0.340%

    No Known Activations