© 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. 120463
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    selection, voluntary, dependent, compounding

    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
    ardi
    0.49
     ९
    0.46
    adani
    0.45
     nói
    0.45
    esis
    0.44
    hee
    0.42
    arko
    0.42
    issi
    0.42
     сня
    0.41
    assi
    0.41
    POSITIVE LOGITS
    Herkese
    0.55
     Furnace
    0.50
    Lycodon
    0.50
     különb
    0.50
    म्प
    0.48
    敝
    0.47
    γεν
    0.46
     penyel
    0.46
     COURSE
    0.45
    Mystery
    0.45
    Activations Density 0.000%

    No Known Activations