© 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. 84535
    Prev
    Next
    INDEX
    Explanations

    academic document descriptions

    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
     before
    -2.11
     with
    -2.03
     their
    -1.98
     that
    -1.95
     on
    -1.93
     various
    -1.63
     during
    -1.62
     üblichen
    -1.58
     in
    -1.58
     even
    -1.57
    POSITIVE LOGITS
     manifeste
    1.51
     ieri
    1.46
    摃
    1.44
    ATIC
    1.41
    踅
    1.38
     relata
    1.36
     intrig
    1.36
     evit
    1.35
     humeur
    1.34
     capot
    1.34
    Activations Density 0.230%

    No Known Activations