© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4907
    Prev
    Next
    INDEX
    Explanations

    wine salon

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

    station names and numbers

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

    text written in Slavic languages, particularly Serbian/Croatian/Bosnian.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     muß
    1.27
    colour
    1.18
     sólo
    1.17
     daß
    1.13
     եւ
    1.11
    ﯾ
    1.11
     μία
    1.09
     Sólo
    1.07
    ﯿ
    1.05
     şi
    1.04
    POSITIVE LOGITS
     gde
    1.13
     și
    1.03
     определён
    1.01
     oraș
    1.00
     creș
    1.00
     ș
    0.99
     Ș
    0.95
     posle
    0.95
     enggak
    0.93
    щё
    0.93
    Activations Density 0.004%

    No Known Activations