© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9181
    Prev
    Next
    INDEX
    Explanations

    fancy-schmancy

    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_31_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
    
    0.52
     replicate
    0.50
     hypoc
    0.49
     riveting
    0.49
     munitions
    0.48
     maps
    0.47
     virgin
    0.46
    acirc
    0.46
     NPD
    0.46
     proxim
    0.46
    POSITIVE LOGITS
    ཌ
    0.68
    斯科
    0.59
    福
    0.55
    ABOR
    0.53
    Ре
    0.53
    Ро
    0.53
     Bhubaneswar
    0.52
     Ро
    0.50
     Το
    0.50
    西
    0.50
    Activations Density 0.002%

    No Known Activations