© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72462
    Prev
    Next
    INDEX
    Explanations

    module.exports assignment

    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
     through
    -0.93
     本店
    -0.93
     because
    -0.89
     did
    -0.89
     or
    -0.89
    ığında
    -0.86
     on
    -0.86
     after
    -0.85
     during
    -0.81
    bufio
    -0.81
    POSITIVE LOGITS
     appeler
    0.91
     conclure
    0.91
     клуба
    0.87
     italiens
    0.87
     prouver
    0.87
    Crystal
    0.86
     répondre
    0.85
     réussir
    0.84
     semblable
    0.84
    !='
    0.84
    Activations Density 0.002%

    No Known Activations