© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7196
    Prev
    Next
    INDEX
    Explanations

    div id class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     полном
    1.24
    ich
    1.21
    外部
    1.17
    icill
    1.16
     incluidos
    1.15
    ellers
    1.13
    纔
    1.08
    rea
    1.08
    цкі
    1.07
    igian
    1.06
    POSITIVE LOGITS
     getter
    1.66
    CRS
    1.42
     assembler
    1.37
    errick
    1.35
     HAVING
    1.31
     packer
    1.27
     fibrin
    1.27
    getter
    1.26
    /~
    1.23
     alumina
    1.22
    Activations Density 0.033%

    No Known Activations