© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184015
    Prev
    Next
    INDEX
    Explanations

    outbound trams, arrivals, departures, rubbish

    np_acts-logits-general · gemini-2.5-flash-lite

    areas, south, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     invasion
    0.43
    但是我
    0.43
    錯
    0.42
    炰
    0.42
    Radiation
    0.42
     malignancy
    0.42
     RADIATION
    0.41
     radiation
    0.41
    麴
    0.41
    寔
    0.41
    POSITIVE LOGITS
     peł
    0.55
    ین
    0.50
    ellular
    0.49
     داشته
    0.49
     tujuh
    0.48
    kező
    0.45
    ไอ
    0.45
     위한
    0.45
    ffee
    0.45
    availability
    0.44
    Activations Density 0.000%

    No Known Activations