© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7841
    Prev
    Next
    INDEX
    Explanations

    formation of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesu
    1.78
    tzmann
    1.75
    ⎙
    1.73
    にご
    1.73
     Instr
    1.72
     Virg
    1.68
     สาย
    1.66
    꽉
    1.65
     함수의
    1.64
    Instr
    1.63
    POSITIVE LOGITS
    appropriate
    1.78
    various
    1.57
     appropriate
    1.53
     ilgili
    1.52
     تجویز
    1.52
    合适的
    1.50
     new
    1.50
    eraj
    1.49
    necessary
    1.48
     future
    1.47
    Activations Density 0.090%

    No Known Activations