© 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. 67077
    Prev
    Next
    INDEX
    Explanations

    connected to hyphenated words

    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
     and
    -1.90
     is
    -1.78
    </h2>
    -1.61
     has
    -1.48
     because
    -1.47
     does
    -1.46
     can
    -1.43
     so
    -1.43
     at
    -1.42
     will
    -1.41
    POSITIVE LOGITS
    actrice
    1.84
     adept
    1.81
    奁
    1.69
    糴
    1.69
    螃
    1.66
     británica
    1.65
     brilh
    1.63
    OOTDTY
    1.63
     râ
    1.61
    िटी
    1.60
    Activations Density 0.078%

    No Known Activations