© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 14073
    Prev
    Next
    INDEX
    Explanations

    neural network hallucinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    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
    s
    0.91
    nect
    0.80
    t
    0.80
     Ese
    0.77
    Nc
    0.77
     Aufgabe
    0.76
    ローラー
    0.75
    माण
    0.75
    rified
    0.75
    आप
    0.75
    POSITIVE LOGITS
    cyon
    1.29
    pern
    1.15
    ibur
    1.11
    ifax
    1.08
    iday
    1.04
     perovsk
    1.02
    ibut
    1.00
    ే
    0.93
    ucin
    0.92
    ucine
    0.91
    Activations Density 0.038%

    No Known Activations