© 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. 14281
    Prev
    Next
    INDEX
    Explanations

    named entities 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
    ляция
    -1.65
    人的
    -1.61
    ść
    -1.60
     '+':
    -1.57
     numerous
    -1.55
    鎗
    -1.55
     contextLoads
    -1.52
     Really
    -1.49
     lutego
    -1.48
     '*':
    -1.47
    POSITIVE LOGITS
     of
    1.63
     información
    1.45
    .
    1.45
    の内容
    1.41
     volle
    1.40
     يكون
    1.39
     testé
    1.39
     للن
    1.35
     акции
    1.32
    が終わ
    1.30
    Activations Density 0.595%

    No Known Activations