© 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. 99960
    Prev
    Next
    INDEX
    Explanations

    renting and delivery services

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

    code definition and programming

    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
    関西
    0.48
    kjhtml
    0.46
    rental
    0.44
    い
    0.44
    रील
    0.44
     война
    0.43
    videmment
    0.43
    ༞
    0.43
    pairwise
    0.43
    豁
    0.43
    POSITIVE LOGITS
     Root
    0.54
     Insect
    0.52
     Slate
    0.50
     TDS
    0.50
     i
    0.50
     Job
    0.49
     delivery
    0.49
     Rabin
    0.49
     Worker
    0.49
     Delivery
    0.48
    Activations Density 0.000%

    No Known Activations