© 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. 16663
    Prev
    Next
    INDEX
    Explanations

    illusory sights and sounds

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

    visual distortion, blurriness, dancing colors

    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
     Themen
    0.43
    خب
    0.43
     Crane
    0.43
    壳
    0.42
     работы
    0.41
    蔫
    0.41
    愍
    0.41
    醒
    0.40
     خب
    0.39
     crou
    0.39
    POSITIVE LOGITS
     illusory
    0.73
     illusions
    0.69
     blurred
    0.66
     hallucinations
    0.66
     illusion
    0.63
     halluc
    0.63
    blurred
    0.63
     distortions
    0.62
     blurry
    0.61
     distorted
    0.61
    Activations Density 0.062%

    No Known Activations