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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54197
    Prev
    Next
    INDEX
    Explanations

    actors uniting and collaborating

    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
     while
    -1.66
     when
    -1.66
     after
    -1.64
     if
    -1.64
     before
    -1.52
     several
    -1.52
     four
    -1.48
     three
    -1.48
     or
    -1.47
     what
    -1.46
    POSITIVE LOGITS
     who
    1.30
     together
    1.27
     rendement
    1.23
     ovale
    1.23
    ’
    1.16
     enthou
    1.16
     united
    1.15
     tirs
    1.14
     forment
    1.13
     gracilis
    1.13
    Activations Density 0.045%

    No Known Activations