© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1259
    Prev
    Next
    INDEX
    Explanations

    hallucinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    íe
    0.91
    َة
    0.81
    スの
    0.81
    íes
    0.80
    ﻊ
    0.78
    ﺐ
    0.77
    ème
    0.77
    ிக்
    0.76
    트는
    0.76
    ὴ
    0.73
    POSITIVE LOGITS
    ฯ
    0.84
    arati
    0.81
    béco
    0.78
    oinette
    0.71
    kowitz
    0.71
     deceit
    0.70
     জাহাঙ্গীর
    0.69
    ricia
    0.69
    atchewan
    0.69
     agradecer
    0.68
    Activations Density 1.037%

    No Known Activations