© 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. 22-GEMMASCOPE-RES-131K
    7. 15758
    Prev
    Next
    INDEX
    Explanations

    React component props

    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_22/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
     to
    -1.14
    ).
    -1.05
    pherds
    -1.02
     نوع
    -0.97
     “
    -0.94
    人的
    -0.93
     многих
    -0.93
    thodox
    -0.91
    bernate
    -0.90
    之后
    -0.90
    POSITIVE LOGITS
    ᅠ
    1.09
    CCIÓN
    1.09
    utilizzo
    1.08
     påvir
    1.08
    thenia
    1.05
    Tempat
    1.02
    Morfo
    1.02
    moduleId
    1.02
    ﻻ
    0.99
    Jangan
    0.99
    Activations Density 0.005%

    No Known Activations