© 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. 107756
    Prev
    Next
    INDEX
    Explanations

    multi-lingual content

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

    foreign languages and names

    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
     destructor
    0.51
    cann
    0.51
    h
    0.50
    q
    0.49
    ز
    0.47
    cb
    0.46
    D
    0.46
    aven
    0.45
    cr
    0.45
    سر
    0.45
    POSITIVE LOGITS
     ቦታ
    0.56
     少し
    0.54
    !।
    0.54
     Пока
    0.53
     Ahora
    0.52
     Dessous
    0.52
     เลือก
    0.52
     Agios
    0.52
     ത
    0.52
     જોવા
    0.52
    Activations Density 0.000%

    No Known Activations