© 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. 21689
    Prev
    Next
    INDEX
    Explanations

    and

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

    Pokemon models

    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
     cittadini
    0.54
     simbolo
    0.52
     E
    0.49
     ciudadanos
    0.48
    ย
    0.47
    לא
    0.47
    ும்
    0.46
    getColor
    0.46
    對
    0.46
    িয়া
    0.46
    POSITIVE LOGITS
    sembles
    0.46
    avidin
    0.45
    an
    0.45
     दुरु
    0.45
    istency
    0.44
     الأعلى
    0.44
     शिखर
    0.43
     jockey
    0.43
     खिच
    0.43
     어떻게
    0.42
    Activations Density 0.000%

    No Known Activations