© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108870
    Prev
    Next
    INDEX
    Explanations

    report and reply

    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_34/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
     Président
    -0.89
     visse
    -0.86
    ᚄ
    -0.85
     plante
    -0.85
    dstuk
    -0.83
    setOutput
    -0.82
     welkom
    -0.81
     coupable
    -0.80
     aspi
    -0.79
     fortal
    -0.79
    POSITIVE LOGITS
     reply
    2.11
     report
    1.52
     Report
    1.51
     Reply
    1.48
    Reply
    1.34
    Report
    1.34
     replies
    1.27
     replied
    1.27
    REPLY
    1.23
    REPORT
    1.21
    Activations Density 0.034%

    No Known Activations