© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129663
    Prev
    Next
    INDEX
    Explanations

    begin/end blocks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    囁
    -1.36
    それにしても
    -1.34
    もあった
    -1.22
    婠
    -1.18
     FURTHER
    -1.17
     дальней
    -1.12
    possibly
    -1.09
    うーん
    -1.08
    heds
    -1.08
    still
    -1.08
    POSITIVE LOGITS
     of
    1.30
     are
    1.23
     new
    1.20
     have
    1.19
     from
    1.13
     Unlike
    1.09
    j
    1.05
    Most
    1.03
    L
    1.03
    大多
    1.02
    Activations Density 0.003%

    No Known Activations