© 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. 224480
    Prev
    Next
    INDEX
    Explanations

    illusion and hallucination

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

    Cat-Cow pose

    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
     dưỡng
    0.51
    uksi
    0.50
    獸
    0.49
    そうだ
    0.48
    lighet
    0.48
    ishna
    0.48
    кса
    0.47
     সত্যিকারের
    0.47
    yny
    0.46
     স্বচ্ছ
    0.46
    POSITIVE LOGITS
    ad
    0.49
     illusion
    0.45
    d
    0.43
     discontinuity
    0.43
    迈
    0.42
    ด์
    0.42
    gar
    0.42
     halluc
    0.42
    f
    0.41
    illusion
    0.41
    Activations Density 0.000%

    No Known Activations