© 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. 182553
    Prev
    Next
    INDEX
    Explanations

    stow vertical

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

    extreme qualification

    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
    for
    0.56
    count
    0.51
    csdn
    0.51
    as
    0.50
    ਾ
    0.50
    nych
    0.49
    first
    0.48
    fica
    0.47
    c
    0.47
    பா
    0.46
    POSITIVE LOGITS
     modernity
    0.50
     callous
    0.50
     учреждения
    0.50
     ব্যতীত
    0.49
     eliminates
    0.48
     ridicule
    0.48
     vosotros
    0.48
     godly
    0.48
     manuss
    0.48
     Sang
    0.47
    Activations Density 0.001%

    No Known Activations