© 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. 14656
    Prev
    Next
    INDEX
    Explanations

    python code operations

    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
    ,
    1.13
    :
    1.08
     dall
    0.98
     sull
    0.97
     shr
    0.92
     confronti
    0.91
     coined
    0.89
    がき
    0.89
     capo
    0.88
     plaint
    0.88
    POSITIVE LOGITS
    то
    1.17
    ürlich
    1.04
    ています
    1.02
    oretically
    1.01
    otá
    0.97
    버
    0.96
    ného
    0.95
    瞍
    0.95
    šću
    0.93
    ι
    0.92
    Activations Density 0.167%

    No Known Activations