© 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. 84075
    Prev
    Next
    INDEX
    Explanations

    nutrition counseling

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

    days of the week and specific nouns

    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
     $\
    0.46
    🙈
    0.46
    👐
    0.45
     Parcel
    0.45
    列
    0.45
    。)
    0.44
    🙉
    0.44
     Flu
    0.43
     Donor
    0.43
    😐
    0.43
    POSITIVE LOGITS
     affirms
    0.52
     verwij
    0.49
    pil
    0.47
    testimon
    0.46
     zdrow
    0.46
    plements
    0.44
    carta
    0.44
    todos
    0.43
     वोट
    0.43
    professor
    0.43
    Activations Density 0.000%

    No Known Activations