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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10503
    Prev
    Next
    INDEX
    Explanations

    what programming permits

    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
    कायदा
    0.76
    rita
    0.75
    Notation
    0.74
     ดู
    0.70
     буква
    0.70
    Nad
    0.70
     đươ
    0.69
    <unused2223>
    0.69
    Nast
    0.69
    <unused2165>
    0.68
    POSITIVE LOGITS
     permit
    1.72
     allows
    1.70
     permits
    1.65
     allow
    1.62
     permite
    1.59
     permitting
    1.55
     Allows
    1.50
    allows
    1.48
    允许
    1.47
     позволяет
    1.43
    Activations Density 0.174%

    No Known Activations