© 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. 59581
    Prev
    Next
    INDEX
    Explanations

    her relationships and works

    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
    焄
    -2.52
    d
    -2.41
     meisten
    -2.17
    ⩴
    -2.16
    thirds
    -2.14
    嫘
    -2.13
    ophageal
    -2.11
    ça
    -2.09
    i
    -2.08
    嗚
    -2.08
    POSITIVE LOGITS
     ‘‘
    2.59
     vacía
    2.52
    ’
    2.33
     \
    2.14
     beschä
    2.11
     gebildet
    2.09
    Océ
    2.09
    事實
    2.09
    1
    2.06
    Of
    2.03
    Activations Density 0.007%

    No Known Activations