© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5088
    Prev
    Next
    INDEX
    Explanations

    x-ray

    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
    unks
    1.25
    淹
    1.10
    supseteq
    1.03
    findung
    1.03
    盂
    1.02
     summa
    1.02
    ลัง
    1.02
    Појединачна
    1.01
    discard
    1.01
     teard
    1.01
    POSITIVE LOGITS
    NUMX
    3.88
    oxo
    3.17
    treme
    3.06
    ʷ
    2.83
    cellent
    2.73
    planatory
    2.69
    posure
    2.63
    adecimal
    2.60
    xer
    2.60
    óch
    2.59
    Activations Density 0.266%

    No Known Activations