© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128966
    Prev
    Next
    INDEX
    Explanations

    code followed by punctuation

    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
     with
    -1.44
     from
    -1.42
     by
    -1.37
     in
    -1.26
     of
    -1.19
     part
    -1.14
     being
    -1.13
     like
    -1.12
     at
    -1.10
     also
    -1.09
    POSITIVE LOGITS
    在一起
    1.13
    这是一
    1.07
    据说
    1.05
    。<
    1.05
    と思って
    1.05
     algumas
    1.05
     getrennt
    1.05
    我們
    1.03
    arbeiter
    1.00
    そして
    1.00
    Activations Density 0.008%

    No Known Activations