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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6655
    Prev
    Next
    INDEX
    Explanations

    stigmata, disclaimer, deceptive, dislike, deals

    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
    说
    0.57
    ，
    0.47
    ين
    0.46
    其他
    0.46
     sole
    0.44
    ங்கிணை
    0.43
     resolvers
    0.42
    䯩
    0.42
    se
    0.42
    有机会
    0.42
    POSITIVE LOGITS
    udging
    0.55
    ipped
    0.50
    dır
    0.50
    Após
    0.50
    s
    0.50
    asını
    0.49
    SON
    0.49
    pOt
    0.49
    aver
    0.49
    ्स
    0.48
    Activations Density 0.278%

    No Known Activations