© 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. 72794
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

    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
    -1.34
     one
    -1.33
     not
    -1.27
     ilustracji
    -1.27
     just
    -1.26
     goes
    -1.23
     our
    -1.20
     in
    -1.19
     also
    -1.18
     an
    -1.17
    POSITIVE LOGITS
    both
    1.27
     CURRENT
    1.27
    那时候
    1.25
    腭
    1.23
     _.
    1.21
     offiziell
    1.21
     valoraciones
    1.17
     obce
    1.17
     escreveu
    1.16
     ____________
    1.15
    Activations Density 0.001%

    No Known Activations