© 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. 10-GEMMASCOPE-RES-131K
    7. 86645
    Prev
    Next
    INDEX
    Explanations

    pulsing, pulsed, pulsatile

    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
     (‘
    -2.19
    鬟
    -2.13
     ‘
    -2.13
     numerosos
    -2.08
    </h3>
    -2.00
     ‘’
    -1.91
    0
    -1.91
     hermosos
    -1.89
     immense
    -1.88
     Niemand
    -1.86
    POSITIVE LOGITS
    })$,
    2.28
    </b>
    2.08
    o
    2.05
     "
    1.99
    le
    1.98
    a
    1.97
     镇
    1.95
    \
    1.95
     $=$
    1.91
    $
    1.90
    Activations Density 0.014%

    No Known Activations