© 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. 34-GEMMASCOPE-RES-131K
    7. 78495
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
     télécharger
    -0.92
     lì
    -0.91
     zichzelf
    -0.90
     Tires
    -0.90
     kolei
    -0.87
     می‌شود
    -0.86
     vendu
    -0.86
     espécie
    -0.85
     themselves
    -0.84
    untitled
    -0.84
    POSITIVE LOGITS
     and
    1.52
     only
    1.28
     or
    1.26
     also
    1.20
     ONLY
    1.19
    only
    1.13
     Only
    1.06
     prior
    1.04
     evening
    1.00
    Only
    0.99
    Activations Density 0.001%

    No Known Activations