© 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. 128346
    Prev
    Next
    INDEX
    Explanations

    you are not alone

    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
     what
    -1.66
     everything
    -1.61
    </h3>
    -1.59
     something
    -1.56
    rassing
    -1.54
     nothing
    -1.52
     the
    -1.52
     how
    -1.45
     actually
    -1.45
     If
    -1.43
    POSITIVE LOGITS
    </b>
    1.69
    没能
    1.54
     culmin
    1.47
    "];
    1.45
    </sup>
    1.45
    #![
    1.41
    ")));
    1.41
     GETS
    1.40
     inay
    1.40
     mily
    1.39
    Activations Density 0.008%

    No Known Activations