© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    setting location

    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
     정말
    1.21
     really
    1.18
    보고
    1.14
     seemingly
    1.13
     mistakes
    1.12
     즐
    1.11
     headaches
    1.10
     appreciate
    1.09
     REALLY
    1.09
     보고
    1.07
    POSITIVE LOGITS
    engel
    1.31
    princ
    1.26
    nine
    1.23
    carlo
    1.23
    élève
    1.21
     formando
    1.20
     _{(
    1.20
    omethyl
    1.18
    forming
    1.18
    érin
    1.18
    Activations Density 0.061%

    No Known Activations