© 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. 67385
    Prev
    Next
    INDEX
    Explanations

    event and occasion contexts

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

    demonstrated impressive / remarkable

    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
    detect
    0.57
     on
    0.54
    critical
    0.52
    delete
    0.51
    detected
    0.48
    म
    0.48
     Brady
    0.47
    при
    0.47
    main
    0.46
     інші
    0.46
    POSITIVE LOGITS
    𝙎
    0.48
     academies
    0.47
     vestibular
    0.47
     وير
    0.46
     آب
    0.46
    starcore
    0.45
    證明
    0.45
     نامه
    0.45
     bureaucratic
    0.44
     dulce
    0.44
    Activations Density 0.001%

    No Known Activations