© 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. 15941
    Prev
    Next
    INDEX
    Explanations

    localization strings, configuration keys

    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
     to
    -1.56
     in
    -1.44
     from
    -1.42
     by
    -1.38
     on
    -1.36
     because
    -1.34
     of
    -1.33
     as
    -1.30
     undeniably
    -1.24
    ردن
    -1.21
    POSITIVE LOGITS
     ..........
    1.63
     .........
    1.59
     alcune
    1.59
     alguns
    1.52
     .......
    1.51
     stalwart
    1.49
     ........
    1.49
     ___________
    1.45
     alcuni
    1.44
    ..........
    1.43
    Activations Density 0.005%

    No Known Activations