© 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. 79584
    Prev
    Next
    INDEX
    Explanations

    kept in storage for years

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

    lock screen, leave it, often a

    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
    📆
    0.48
    📈
    0.46
     输出
    0.46
    🚇
    0.46
    📅
    0.45
     blockbuster
    0.45
    无论是
    0.45
     akár
    0.45
     Jurassic
    0.45
    业界
    0.45
    POSITIVE LOGITS
     motionless
    0.50
    弁
    0.50
    бо
    0.49
    臉
    0.48
     crock
    0.46
     painless
    0.46
     neglected
    0.45
    nahmen
    0.45
     laying
    0.45
     overlooked
    0.44
    Activations Density 0.005%

    No Known Activations