© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 11913
    Prev
    Next
    INDEX
    Explanations

    attractions and sights

    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
    ’
    1.72
     canceled
    1.34
    
    1.30
    !’
    1.30
     half
    1.26
     erased
    1.26
     $
    1.20
     ‘
    1.20
    ര്‍
    1.20
    )');
    1.20
    POSITIVE LOGITS
    Não
    1.62
    ية
    1.42
    يمكن
    1.41
    Archivo
    1.39
     ಕಾನೂ
    1.39
    ία
    1.36
    Kö
    1.36
    ير
    1.35
    াই
    1.34
     değildir
    1.34
    Activations Density 0.048%

    No Known Activations