© 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. 16030
    Prev
    Next
    INDEX
    Explanations

    meaning, step, lines, pp, ID, p, Señor, {'

    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
     other
    -1.45
     those
    -1.40
     because
    -1.38
     these
    -1.26
     out
    -1.24
     should
    -1.20
     people
    -1.20
     which
    -1.15
     spurred
    -1.12
     just
    -1.11
    POSITIVE LOGITS
     alcune
    1.42
     quintessential
    1.34
     trám
    1.30
     relentless
    1.28
     horrifying
    1.27
     delightfully
    1.26
     ridiculously
    1.26
     magnificent
    1.23
     dreadful
    1.22
     remarkably
    1.21
    Activations Density 0.022%

    No Known Activations