© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12639
    Prev
    Next
    INDEX
    Explanations

    implies and suggests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     urs
    1.08
     guidelines
    1.06
    ¸
    1.05
     digit
    1.05
     bricks
    1.04
     ​​
    1.03
    
    1.00
     supplementary
    0.97
    \_
    0.95
    রূপে
    0.94
    POSITIVE LOGITS
    ᓂ
    1.74
    𒁳
    1.68
    которые
    1.58
    feier
    1.57
    ʀ
    1.56
    𝒹
    1.54
    ktiv
    1.54
    ('$
    1.53
    ',['
    1.50
    Iddict
    1.49
    Activations Density 0.126%

    No Known Activations