© 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. 34022
    Prev
    Next
    INDEX
    Explanations

    titles and proper names

    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
     in
    -1.88
     with
    -1.77
     their
    -1.65
     this
    -1.59
     and
    -1.59
     from
    -1.57
     undeniably
    -1.54
     longstanding
    -1.48
     or
    -1.46
     ostensibly
    -1.44
    POSITIVE LOGITS
     rác
    1.68
     alcune
    1.45
     ainda
    1.40
    ౬
    1.34
     alguns
    1.32
    could
    1.30
     カーディガン
    1.29
     alcuni
    1.29
     unsettling
    1.28
    igth
    1.27
    Activations Density 0.116%

    No Known Activations