© 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. 6611
    Prev
    Next
    INDEX
    Explanations

    . prone, . offers, . can, . but, . free

    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
    י
    1.20
    א
    1.13
    ка
    1.07
    ي
    1.00
    스와
    0.96
     અથવા
    0.95
    k
    0.93
    ك
    0.92
    ع
    0.91
    or
    0.89
    POSITIVE LOGITS
    \")
    1.04
    )
    1.00
    ți
    0.96
    \%)
    0.96
    $
    0.96
    ")
    0.94
    ții
    0.91
    )$
    0.88
    \
    0.88
     chắn
    0.87
    Activations Density 0.231%

    No Known Activations