© 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. 10-GEMMASCOPE-RES-131K
    7. 39083
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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_10/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
    \}$,
    -1.34
     attendu
    -1.32
     איך
    -1.26
    ushu
    -1.25
    像是
    -1.23
    vailing
    -1.19
     aparentemente
    -1.15
     eren
    -1.14
     didn
    -1.10
     aunque
    -1.10
    POSITIVE LOGITS
     our
    1.33
     more
    1.32
     any
    1.31
     these
    1.30
     this
    1.26
     також
    1.26
    foundland
    1.17
    otrop
    1.14
    enumerate
    1.13
     many
    1.12
    Activations Density 0.062%

    No Known Activations