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-16K
    4. 875
    Prev
    Next
    INDEX
    Explanations

    principles

    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_16k_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
     हेतु
    1.37
    即可
    1.33
    므로
    1.29
    および
    1.28
     तथा
    1.26
     Subsequently
    1.20
     نیز
    1.19
     및
    1.18
    具有
    1.17
     său
    1.17
    POSITIVE LOGITS
     kinda
    2.54
     yeah
    2.12
     guys
    1.93
     gonna
    1.92
    っていう
    1.89
     really
    1.88
     żeby
    1.85
     crazy
    1.85
     একটা
    1.84
     pretty
    1.82
    Activations Density 2.135%

    No Known Activations