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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8389
    Prev
    Next
    INDEX
    Explanations

    Poliza

    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
    9
    0.55
     reforms
    0.51
    <sup>
    0.50
    il
    0.50
    ol
    0.49
    mile
    0.49
    c
    0.49
     partners
    0.48
     سازمان
    0.48
    <h5>
    0.48
    POSITIVE LOGITS
    ຖື
    0.50
     Bunu
    0.49
     Except
    0.45
     който
    0.44
     Matemática
    0.43
     Pokud
    0.43
     Unless
    0.43
     Jeśli
    0.43
    કની
    0.43
     випадку
    0.42
    Activations Density 0.125%

    No Known Activations