Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47007
    Prev
    Next
    INDEX
    Explanations

    training data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sake
    1.13
     Positioning
    1.05
     thế
    1.03
    യാണ
    1.01
     Nazis
    1.00
    yun
    0.97
    Ր
    0.96
     использова
    0.95
    บอก
    0.94
    再
    0.94
    POSITIVE LOGITS
    ிக்க
    1.23
     geest
    1.12
    igheter
    1.11
    credible
    1.11
     giornal
    1.11
     welchem
    1.11
     %>%
    1.10
     adhé
    1.10
     echte
    1.09
     eigene
    1.08
    Activations Density 0.000%

    No Known Activations