© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1077
    Prev
    Next
    INDEX
    Explanations

    non-english speaking contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     corpses
    1.12
     یا
    1.05
    ).
    1.00
    Fuck
    1.00
     killers
    0.96
     or
    0.96
    )-
    0.95
     "").
    0.94
     crap
    0.93
     или
    0.93
    POSITIVE LOGITS
     nossa
    1.26
    我已经
    1.22
     Estou
    1.20
     আমার
    1.17
    我也
    1.16
     minhas
    1.16
     saya
    1.15
     minha
    1.14
     нашей
    1.12
    につきまして
    1.12
    Activations Density 2.675%

    No Known Activations