© 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. 242936
    Prev
    Next
    INDEX
    Explanations

    time, minutes, foreign words

    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
    t
    0.59
    tu
    0.48
    totally
    0.48
    sse
    0.47
    pr
    0.46
     \
    0.46
    決して
    0.46
    amin
    0.46
    err
    0.45
    set
    0.45
    POSITIVE LOGITS
    זה
    0.50
     dinámica
    0.49
     año
    0.48
    
    0.48
     señor
    0.48
    麃
    0.47
     senhor
    0.47
    מס
    0.47
     mía
    0.46
     léger
    0.46
    Activations Density 0.002%

    No Known Activations