© 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. 43750
    Prev
    Next
    INDEX
    Explanations

    ls commands

    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
     ด้วย
    -1.45
     SHOULD
    -1.43
    Koordinaten
    -1.34
     cuadrada
    -1.30
     schnell
    -1.29
     یکی
    -1.29
     که
    -1.27
    以上
    -1.26
    ೦
    -1.25
     gleichen
    -1.23
    POSITIVE LOGITS
    </strong>
    1.60
    stě
    1.42
     nyní
    1.40
     on
    1.38
     sembrano
    1.31
    さを
    1.27
     teď
    1.27
    ～　
    1.22
     ceket
    1.21
     acreditar
    1.21
    Activations Density 0.050%

    No Known Activations