© 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. 10770
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

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

    phrases starting with "All"

    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
    Government
    0.50
     jobId
    0.42
    Various
    0.42
     койма
    0.42
    ші
    0.42
     getSupport
    0.42
    NavController
    0.41
    ⮚
    0.40
    Corresponding
    0.40
    Actor
    0.39
    POSITIVE LOGITS
    igator
    0.68
     All
    0.58
    igators
    0.57
    iances
    0.55
    ures
    0.49
    rights
    0.49
    umni
    0.48
     Tất
    0.48
     đều
    0.46
     Rights
    0.45
    Activations Density 0.055%

    No Known Activations