© 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. 1347
    Prev
    Next
    INDEX
    Explanations

    Please remember or read

    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
    에도
    1.82
    か
    1.80
     essais
    1.73
    であ
    1.72
     prowess
    1.68
    nél
    1.66
    一方で
    1.66
    ন
    1.66
    ການ
    1.65
     agh
    1.63
    POSITIVE LOGITS
    ാൻ
    1.99
    كم
    1.94
    annte
    1.77
    hg
    1.70
    ؟!
    1.68
     Pals
    1.64
    ್‌
    1.53
    utrient
    1.53
    uasion
    1.52
    ?'
    1.52
    Activations Density 0.119%

    No Known Activations