© 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. 8192
    Prev
    Next
    INDEX
    Explanations

    onboard systems and features

    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
     Kontexten
    -2.27
     has
    -2.19
    ruguay
    -2.14
    y
    -2.13
    ꒥
    -2.11
     Mitteln
    -2.05
    and
    -2.00
    而
    -1.99
     was
    -1.98
    และ
    -1.95
    POSITIVE LOGITS
    瓛
    2.63
    浤
    2.53
    ༷
    2.36
    ஂ
    2.33
    逡
    2.30
    摃
    2.28
    ⼗
    2.25
    憔
    2.25
    蕓
    2.20
    ครื่อง
    2.19
    Activations Density 0.003%

    No Known Activations