© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 34947
    Prev
    Next
    INDEX
    Explanations

    startle or freeze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     периоди
    0.45
     periodically
    0.44
    限界
    0.44
    不斷
    0.43
    踱
    0.43
     occasional
    0.42
     Hours
    0.41
    слав
    0.41
     occasionally
    0.41
    occas
    0.40
    POSITIVE LOGITS
     startled
    1.09
     surprised
    0.89
     shocked
    0.85
     surprise
    0.75
     stunned
    0.73
     froze
    0.72
     shock
    0.71
     instantly
    0.68
    怔
    0.68
    惊讶
    0.68
    Activations Density 0.001%

    No Known Activations