© 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. 39754
    Prev
    Next
    INDEX
    Explanations

    normal followed by a state or noun

    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
    </strong>
    -1.38
    گاب
    -1.36
     porción
    -1.34
    ticularly
    -1.33
    ("")]
    -1.33
    撳
    -1.30
     někter
    -1.28
    куль
    -1.28
    绻
    -1.28
     niektor
    -1.27
    POSITIVE LOGITS
    you
    1.70
    ",
    1.65
    You
    1.54
     normal
    1.48
    ↵
    1.45
    to
    1.37
    PS
    1.35
    Because
    1.32
    normal
    1.32
    IS
    1.32
    Activations Density 0.067%

    No Known Activations