© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64051
    Prev
    Next
    INDEX
    Explanations

    numbers and time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    с
    0.50
     Sam
    0.46
     νό
    0.45
     Revolución
    0.44
     Mills
    0.44
     যেকোনো
    0.43
     غیر
    0.43
     Чу
    0.43
     люди
    0.42
     enlightening
    0.42
    POSITIVE LOGITS
     hade
    0.47
     conseguir
    0.47
     promo
    0.45
    ുകൊണ്ടാണ്
    0.45
    釭
    0.45
    Distribution
    0.43
     sehe
    0.43
    묶
    0.43
     då
    0.42
    Medical
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.