© 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. 111295
    Prev
    Next
    INDEX
    Explanations

    realize how, verge of, understand where

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

    constantly, far, controversial

    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
    ce
    0.59
    set
    0.56
    1
    0.54
    ter
    0.54
    nd
    0.52
    with
    0.52
    ila
    0.52
     glitch
    0.52
    th
    0.50
    ır
    0.50
    POSITIVE LOGITS
    ového
    0.53
    spruch
    0.51
    敝
    0.51
     Rout
    0.50
     Pued
    0.50
     Donde
    0.49
    둴
    0.48
     Hodges
    0.46
     Donnie
    0.46
     Hospice
    0.46
    Activations Density 0.000%

    No Known Activations