© 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. 86318
    Prev
    Next
    INDEX
    Explanations

    code, questions, and specific entities

    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
     wuß
    -2.81
    käse
    -2.59
    乆
    -2.45
     This
    -2.44
    CurtirCurtir
    -2.39
     antworte
    -2.36
     nothwendig
    -2.25
     erklär
    -2.23
     hacían
    -2.17
    
    -2.17
    POSITIVE LOGITS
    ’
    2.70
    }
    2.44
    &
    2.38
    鲼
    2.25
     grows
    2.25
    圌
    2.25
    ⸥
    2.14
    "
    2.14
     saves
    2.11
    朝から
    2.02
    Activations Density 0.002%

    No Known Activations