© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 197508
    Prev
    Next
    INDEX
    Explanations

    Swiss national

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

    quartz tube

    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
     неизвест
    0.51
     बेरोज
    0.50
     बेरोजगारी
    0.49
    ኡ
    0.48
     успешно
    0.47
    ረስ
    0.47
     бесплатно
    0.47
     fraudulently
    0.46
     учун
    0.45
    язку
    0.45
    POSITIVE LOGITS
    &=\
    0.55
    &
    0.51
    leaf
    0.47
    STR
    0.46
    myt
    0.46
    hten
    0.45
    %
    0.45
    yl
    0.45
    km
    0.45
    lings
    0.45
    Activations Density 0.001%

    No Known Activations