© 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. 9164
    Prev
    Next
    INDEX
    Explanations

    if conditions and data

    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
    ូច
    0.57
     cholester
    0.57
     вле
    0.56
    
    0.55
     SPMs
    0.54
     బంగ
    0.54
     част
    0.53
    ahooks
    0.53
    ˇ
    0.53
    altung
    0.52
    POSITIVE LOGITS
    ↵↵
    0.64
     Through
    0.61
    Through
    0.59
     Para
    0.52
     Max
    0.52
     Tor
    0.52
     through
    0.50
    ware
    0.50
    annot
    0.50
     Annot
    0.50
    Activations Density 0.003%

    No Known Activations