© 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. 129281
    Prev
    Next
    INDEX
    Explanations

    est compounds and spark

    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
    vantaged
    -3.92
    $
    -3.81
    öpfer
    -3.48
    鹉
    -3.44
    følgelig
    -3.34
    蹋
    -3.17
    CHREIB
    -3.13
    愎
    -3.08
    髏
    -3.05
    ーズン
    -2.84
    POSITIVE LOGITS
    ing
    5.28
    er
    4.25
    ed
    3.88
    o
    3.61
    ie
    3.11
    en
    3.09
    न
    3.03
    an
    3.00
    u
    2.95
    胧
    2.94
    Activations Density 0.025%

    No Known Activations