© 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. 77818
    Prev
    Next
    INDEX
    Explanations

    performance incidents

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

    Instagram and Telegram API bots

    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
    ز
    0.54
    би
    0.54
    ни
    0.52
    Attendees
    0.51
    इस
    0.50
    ም
    0.48
    ही
    0.47
    î
    0.47
    ի
    0.47
    чай
    0.47
    POSITIVE LOGITS
     segno
    0.48
    ளுடைய
    0.45
    ".*:
    0.43
     metas
    0.42
     "^
    0.41
     "&
    0.40
     sentado
    0.40
     tantamount
    0.40
     வயி
    0.40
     stuffing
    0.39
    Activations Density 0.002%

    No Known Activations