© 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. 12817
    Prev
    Next
    INDEX
    Explanations

    end-of-studies project needs

    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
    Negative Logits
     screech
    1.66
    écou
    1.58
    eca
    1.56
    eeq
    1.55
    refixer
    1.55
    ྫ
    1.50
     steepest
    1.49
    ྐ
    1.49
    LOP
    1.48
    getKeyCode
    1.44
    POSITIVE LOGITS
     Ctrl
    1.37
    lık
    1.35
    دة
    1.26
    meta
    1.26
     فَ
    1.23
     rested
    1.20
    reise
    1.20
    lyk
    1.20
    ता
    1.19
    ifying
    1.18
    Activations Density 0.000%

    No Known Activations