© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3106
    Prev
    Next
    INDEX
    Explanations

    machining, parsing, Lexical, Svensk

    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_12_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
     Перейти
    2.25
    埗
    1.94
    которые
    1.72
    ancellation
    1.68
     others
    1.60
    дцать
    1.58
     nothing
    1.58
    锏
    1.51
     behalf
    1.51
     Others
    1.51
    POSITIVE LOGITS
    ه
    7.51
    的
    7.32
    e
    7.10
    a
    7.00
    s
    6.75
    י
    6.31
    을
    6.24
    o
    6.16
    i
    6.14
    ي
    6.09
    Activations Density 1.549%

    No Known Activations