© 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. 127994
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

    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
    ’
    -3.09
    </b>
    -2.59
    または
    -2.48
     stifled
    -2.45
    replyreport
    -2.42
    7
    -2.34
     όταν
    -2.31
    ㌧
    -2.19
     persino
    -2.14
    Ꮟ
    -2.14
    POSITIVE LOGITS
    .
    3.23
    stücks
    2.61
    </h3>
    2.52
    镦
    2.42
    lgari
    2.41
    讠
    2.34
     cambiar
    2.27
    ࿊
    2.27
    their
    2.19
    ቫ
    2.19
    Activations Density 0.005%

    No Known Activations