© 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. 163054
    Prev
    Next
    INDEX
    Explanations

    people, places, and actions

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

    retiring internal auditor

    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
     ನೋಡ
    0.59
     Ovaj
    0.57
    ណ្
    0.56
     chargés
    0.56
     тела
    0.55
     ሆ
    0.55
     रात
    0.55
     세계
    0.55
     buhay
    0.55
     ער
    0.54
    POSITIVE LOGITS
    Trivia
    0.52
    ’
    0.46
    基础设施
    0.44
    ↵↵
    0.43
    t
    0.43
    img
    0.42
    紶
    0.41
    هم
    0.41
    </strong>
    0.41
    两条
    0.41
    Activations Density 0.000%

    No Known Activations