© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1642
    Prev
    Next
    INDEX
    Explanations

    entity class property

    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
     they
    -1.52
    <_>
    -1.47
     timmar
    -1.46
    StandardCharsets
    -1.43
    ::{
    -1.39
    =$((
    -1.34
    ("")
    -1.33
     veckor
    -1.33
     which
    -1.29
    ttää
    -1.27
    POSITIVE LOGITS
    Descriere
    1.29
     instead
    1.25
     diğer
    1.21
    大切に
    1.15
     такі
    1.14
     zamiast
    1.13
     інших
    1.09
     взгляд
    1.08
    Beschrijving
    1.08
     other
    1.08
    Activations Density 0.092%

    No Known Activations