© 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-16K
    7. 5476
    Prev
    Next
    INDEX
    Explanations

    `a` followed by command options

    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_16k_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
    أ
    1.30
    ەک
    1.17
    cí
    1.16
     oscuro
    1.11
    о
    1.11
    ア
    1.11
    お
    1.05
    𝒸
    1.03
    fek
    1.00
     desempeñ
    0.99
    POSITIVE LOGITS
    '
    1.07
    ively
    0.99
    ,
    0.98
    is
    0.97
    enabled
    0.97
    aliases
    0.97
    IL
    0.96
    ism
    0.95
    er
    0.91
    isations
    0.91
    Activations Density 0.004%

    No Known Activations