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. 22-GEMMASCOPE-2-RES-65K
    4. 532
    Prev
    Next
    INDEX
    Explanations

    code punctuation and markup

    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_22_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
     Gly
    0.72
     Rosal
    0.72
     Terminal
    0.66
    .
    0.64
     Julian
    0.64
     Nerv
    0.64
     Wys
    0.64
     Dors
    0.62
     Ell
    0.62
    Terminal
    0.62
    POSITIVE LOGITS
     не
    0.82
     पाक
    0.80
     ई
    0.75
     ही
    0.74
     nao
    0.73
     انہ
    0.73
    assertion
    0.72
     अनेक
    0.71
     اث
    0.71
    contest
    0.71
    Activations Density 0.000%

    No Known Activations