© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    status

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

    state and status

    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
    ATHER
    0.52
    SScript
    0.52
    ப்பிரிக்க
    0.52
     శరీర
    0.51
     உரு
    0.50
    嘌
    0.49
     anharmonic
    0.49
    甙
    0.49
     সাহায্যে
    0.48
    ೫
    0.48
    POSITIVE LOGITS
     status
    1.03
    status
    1.00
     statuses
    0.92
     Status
    0.91
     статус
    0.84
     स्टेटस
    0.83
    statuses
    0.77
     STATUS
    0.75
    setStatus
    0.73
     pending
    0.72
    Activations Density 0.055%

    No Known Activations