© 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. 15418
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    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
     how
    -2.23
     should
    -1.95
     there
    -1.95
     why
    -1.82
     had
    -1.79
     shouldn
    -1.76
     íntimo
    -1.55
     was
    -1.54
     is
    -1.46
     needs
    -1.46
    POSITIVE LOGITS
     and
    1.90
    蘗
    1.71
     दोनों
    1.59
    ť
    1.49
    ☫
    1.43
    ㆍ
    1.36
     valamint
    1.34
     ALSO
    1.32
    zzlement
    1.31
    },
    1.27
    Activations Density 0.071%

    No Known Activations