© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75514
    Prev
    Next
    INDEX
    Explanations

    remote sender wirelessly

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

    financial gains or fortune

    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
    Negative Logits
    iku
    0.55
    okane
    0.47
    arni
    0.47
    arli
    0.47
    iela
    0.46
    owią
    0.45
    燮
    0.45
     Party
    0.45
    ystring
    0.45
    閩
    0.45
    POSITIVE LOGITS
     remand
    0.47
    и
    0.47
     twofold
    0.46
     corre
    0.46
     overlying
    0.43
     graft
    0.43
     dosages
    0.43
     clonal
    0.43
     преимуще
    0.42
    著者
    0.41
    Activations Density 0.000%

    No Known Activations