© 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. 44932
    Prev
    Next
    INDEX
    Explanations

    Arabic names and organizations

    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
     hotelu
    -1.31
     groet
    -1.30
     aina
    -1.29
     ܠ
    -1.28
     forêts
    -1.27
    のまま
    -1.19
     plantes
    -1.17
     soir
    -1.17
     sih
    -1.14
     gespe
    -1.14
    POSITIVE LOGITS
    </em>
    1.62
     will
    1.41
    虽说
    1.24
    balleur
    1.17
    雖
    1.16
    ͭ
    1.16
    textsc
    1.16
    虽
    1.14
     to
    1.13
     although
    1.12
    Activations Density 0.030%

    No Known Activations