© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12779
    Prev
    Next
    INDEX
    Explanations

    tutorials and reviews

    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_262k_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
    ല്ലാത്ത
    0.77
    而是
    0.68
    ent
    0.64
     stuff
    0.64
    ż
    0.63
    즘
    0.63
    월
    0.63
    eqref
    0.63
    ar
    0.63
    calcul
    0.62
    POSITIVE LOGITS
     および
    0.95
     Edition
    0.90
     Guide
    0.89
     및
    0.88
     एवं
    0.87
     และ
    0.85
     مختلف
    0.82
     Luffy
    0.82
    および
    0.82
     مختلفة
    0.82
    Activations Density 0.018%

    No Known Activations