© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60655
    Prev
    Next
    INDEX
    Explanations

    closed, idle, or resting position

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

    is idle

    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
     первую
    0.45
    强制
    0.42
    ห์
    0.42
     כבר
    0.39
     pierwsze
    0.39
    帳に追加
    0.39
     direttamente
    0.39
    愍
    0.39
     recour
    0.38
    䔋
    0.38
    POSITIVE LOGITS
     inactive
    0.87
     resting
    0.85
     idle
    0.84
     Idle
    0.82
    inactive
    0.81
     inactivity
    0.78
    resting
    0.78
     Resting
    0.78
     निष्क्रिय
    0.77
    idle
    0.76
    Activations Density 0.038%

    No Known Activations