© 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. 22-GEMMASCOPE-RES-131K
    7. 27749
    Prev
    Next
    INDEX
    Explanations

    error messages and command usage

    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
     hotelu
    -0.94
    ίνει
    -0.94
    Тай
    -0.92
     triko
    -0.92
    stealth
    -0.90
    !」
    -0.89
    Intellectual
    -0.89
    Дата
    -0.87
     própri
    -0.87
    ίζ
    -0.87
    POSITIVE LOGITS
     only
    1.39
     you
    1.28
     can
    1.13
     please
    1.12
     either
    1.09
     requires
    1.00
     should
    0.98
     required
    0.95
     bądź
    0.95
     use
    0.94
    Activations Density 0.006%

    No Known Activations