© 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. 33585
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     for
    -1.41
     putting
    -1.33
     (
    -1.28
    \
    -1.28
     these
    -1.27
     pushing
    -1.27
     if
    -1.25
     taking
    -1.25
     using
    -1.23
    ’
    -1.23
    POSITIVE LOGITS
     delightfully
    1.45
    ⮑
    1.44
    provides
    1.44
     abd
    1.39
    showed
    1.36
     ſeveral
    1.34
     usando
    1.33
    殽
    1.32
    descri
    1.32
     récemment
    1.30
    Activations Density 0.013%

    No Known Activations