© 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. 50509
    Prev
    Next
    INDEX
    Explanations

    travel and file system contexts

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

    unknown, frequently, original, simply, cause

    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
    жі
    0.53
    등급
    0.47
    مل
    0.45
    冠军
    0.44
    ছিল
    0.43
    يرات
    0.43
    څ
    0.43
    찡
    0.43
     citations
    0.43
    IPA
    0.43
    POSITIVE LOGITS
     பய
    0.59
     പറയാ
    0.55
     powodu
    0.55
    naya
    0.55
    yl
    0.53
    kei
    0.50
     þing
    0.50
    əl
    0.49
    che
    0.48
    kov
    0.47
    Activations Density 0.000%

    No Known Activations