© 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. 195913
    Prev
    Next
    INDEX
    Explanations

    planning processes, altar, says, city, Kirstie, taken

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

    costs and justifying investments

    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
     emerge
    0.52
     underside
    0.48
     탁
    0.48
     hex
    0.47
     silicon
    0.46
     emerges
    0.46
     nowy
    0.45
    os
    0.44
     filo
    0.44
     tendons
    0.43
    POSITIVE LOGITS
    蒨
    0.51
    жают
    0.51
    冼
    0.51
    D
    0.50
    文學
    0.48
    ܤ
    0.48
    皚
    0.48
    HALL
    0.48
    Ä
    0.46
    NIH
    0.46
    Activations Density 0.000%

    No Known Activations