© 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. 34-GEMMASCOPE-RES-131K
    7. 988
    Prev
    Next
    INDEX
    Explanations

    specific phrase intros

    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_34/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
    мето
    -0.82
     tī
    -0.77
     withal
    -0.77
     PowerShell
    -0.75
     loung
    -0.73
    ((((
    -0.71
    vaných
    -0.71
     aang
    -0.70
     (-)
    -0.69
     attested
    -0.69
    POSITIVE LOGITS
     layar
    0.90
     std
    0.83
     quindi
    0.79
    IM
    0.78
     dziś
    0.77
    )\
    0.77
     اسف
    0.77
     Максима
    0.75
    !="
    0.75
     бумаги
    0.75
    Activations Density 0.002%

    No Known Activations