© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14675
    Prev
    Next
    INDEX
    Explanations

    hallucination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     листь
    2.81
    PathDirectory
    2.77
    OLYBD
    2.73
    ridate
    2.69
    ಲ್ಲಿ
    2.68
    岖
    2.68
     заработной
    2.66
    ບບ
    2.66
    GUILayout
    2.63
    ாடு
    2.61
    POSITIVE LOGITS
    <bos>
    2.17
    oo
    2.13
    ्ता
    2.03
    barrel
    2.02
    ting
    2.00
    ته
    1.97
    chef
    1.96
    onyms
    1.93
    يتها
    1.92
    D
    1.91
    Activations Density 0.012%

    No Known Activations