© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6459
    Prev
    Next
    INDEX
    Explanations

    bash shell commands

    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_15_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
     araştırm
    1.63
     bestaan
    1.59
     nivel
    1.52
    oflav
    1.51
    펨
    1.51
     Faiz
    1.47
     katika
    1.47
    opre
    1.47
     Verified
    1.45
     zas
    1.44
    POSITIVE LOGITS
    ホー
    1.50
    buc
    1.47
     Lakeland
    1.35
     pauses
    1.35
     الآخر
    1.32
     hemisphere
    1.32
     "~/
    1.31
     trolley
    1.31
    Tron
    1.29
     الاخر
    1.27
    Activations Density 0.001%

    No Known Activations