© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71776
    Prev
    Next
    INDEX
    Explanations

    Saxon places and software terms

    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
    現象
    -1.52
     странице
    -1.41
    "));
    -1.41
     هایی
    -1.40
    </blockquote>
    -1.31
     subsequently
    -1.29
     provided
    -1.28
    暱
    -1.26
     resulted
    -1.23
     because
    -1.22
    POSITIVE LOGITS
     malgré
    1.29
     الرغم
    1.27
     pasas
    1.26
     expéri
    1.25
     akci
    1.23
     obſ
    1.15
    迓
    1.15
     antes
    1.15
     rése
    1.14
    blusa
    1.13
    Activations Density 0.025%

    No Known Activations