© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71899
    Prev
    Next
    INDEX
    Explanations

    tcolorbox, xcolor, listings

    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
     on
    -1.83
     it
    -1.73
     when
    -1.67
     as
    -1.61
     which
    -1.59
     to
    -1.58
     if
    -1.56
     in
    -1.53
     of
    -1.49
     will
    -1.36
    POSITIVE LOGITS
     THOSE
    1.81
    hezza
    1.74
    Instead
    1.72
    those
    1.66
    дают
    1.63
    Especially
    1.56
    那種
    1.55
     rassemb
    1.52
    Those
    1.50
     COMPLE
    1.50
    Activations Density 0.002%

    No Known Activations