© 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. 224898
    Prev
    Next
    INDEX
    Explanations

    was fired, awaits, took, wrote

    np_acts-logits-general · gemini-2.5-flash-lite

    knowledge cutoff dates

    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
    "
    0.52
     efectuar
    0.49
    ទី
    0.48
     Untersuchungen
    0.44
    ദ്
    0.44
     كبير
    0.44
     financiación
    0.43
     இட
    0.43
    ి
    0.43
    chedule
    0.42
    POSITIVE LOGITS
     asyncio
    0.49
     YMCA
    0.47
     by
    0.47
     Gospel
    0.47
     built
    0.46
     Built
    0.45
     特別
    0.43
    ette
    0.43
    wiata
    0.43
     Metro
    0.42
    Activations Density 0.001%

    No Known Activations