© 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. 44901
    Prev
    Next
    INDEX
    Explanations

    flush buffer output

    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
     you
    -1.79
     then
    -1.53
     they
    -1.49
    .”
    -1.47
    ”.
    -1.46
     it
    -1.40
     też
    -1.40
     ‘
    -1.30
    を読み
    -1.29
     who
    -1.27
    POSITIVE LOGITS
    BigNumber
    1.52
    Jahre
    1.30
    igshid
    1.26
    ynchronous
    1.25
     Revista
    1.23
     to
    1.23
     producen
    1.23
    brainly
    1.23
     milliard
    1.22
    Gruppe
    1.21
    Activations Density 0.007%

    No Known Activations