© 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. 8908
    Prev
    Next
    INDEX
    Explanations

    suspect something

    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
     strides
    1.61
    ين
    1.55
    ic
    1.52
    é
    1.48
    ə
    1.43
     existing
    1.42
    ோ
    1.40
    op
    1.34
     struggles
    1.33
    યા
    1.33
    POSITIVE LOGITS
    $
    1.86
    ING
    1.84
     причем
    1.80
    ת
    1.80
    ATE
    1.78
     rechaz
    1.76
    $("
    1.75
    น
    1.72
    Questo
    1.71
    ్
    1.67
    Activations Density 0.005%

    No Known Activations