© 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. 33631
    Prev
    Next
    INDEX
    Explanations

    demonstrates this

    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
    看去
    -0.91
     izquier
    -0.89
     (!__
    -0.88
    ❔
    -0.88
     påvir
    -0.88
     varones
    -0.88
     guerr
    -0.88
     declaración
    -0.88
    řád
    -0.86
     couteau
    -0.85
    POSITIVE LOGITS
     this
    1.22
     example
    1.19
     illustrates
    1.14
     نشان
    1.12
     demonstrates
    1.05
     reminds
    1.00
    示
    0.98
    ādi
    0.97
    걍
    0.97
     lesson
    0.94
    Activations Density 0.042%

    No Known Activations