© 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. 196486
    Prev
    Next
    INDEX
    Explanations

    floors, residential, capped, extensive, Archive

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

    acronyms and definitions

    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
    ina
    0.57
    del
    0.52
    esehen
    0.48
     కార్డు
    0.48
    th
    0.47
     chien
    0.47
     অভিব্যক্তি
    0.47
    g
    0.47
    laki
    0.46
    thys
    0.46
    POSITIVE LOGITS
     잔
    0.51
     basement
    0.46
     residuals
    0.46
     residential
    0.46
    परीक्षा
    0.45
     camping
    0.44
     furnace
    0.44
     residual
    0.43
     furtherance
    0.43
    噬
    0.43
    Activations Density 0.000%

    No Known Activations