© 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. 197444
    Prev
    Next
    INDEX
    Explanations

    spite of, subject wants, Shift by

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

    describing conditions or states

    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
     Tamaño
    0.45
    p
    0.45
    ປະ
    0.43
    baixo
    0.43
    amek
    0.43
    i
    0.43
    мень
    0.42
    mest
    0.41
    半
    0.41
    accay
    0.41
    POSITIVE LOGITS
     duet
    0.48
     hyperactivity
    0.48
     Δη
    0.48
     ബ്ല
    0.46
     프로그램
    0.45
     luka
    0.45
     تبدیل
    0.45
     terjadinya
    0.45
     그러면
    0.45
     AS
    0.44
    Activations Density 0.001%

    No Known Activations