© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16513
    Prev
    Next
    INDEX
    Explanations

    common following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     or
    -1.63
     any
    -1.56
     should
    -1.44
     will
    -1.36
     from
    -1.30
    就可以了
    -1.27
    部份
    -1.20
     with
    -1.18
    municipi
    -1.17
     in
    -1.16
    POSITIVE LOGITS
     predominantly
    1.31
     ส์
    1.28
    į
    1.25
    during
    1.22
    potentially
    1.22
    Válasz
    1.21
     lopp
    1.20
    roughly
    1.18
    AfterEach
    1.17
    zzá
    1.16
    Activations Density 0.020%

    No Known Activations