© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148661
    Prev
    Next
    INDEX
    Explanations

    in-depth

    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_29_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
     banane
    0.77
     ঘোষণা
    0.76
    RAM
    0.72
    эр
    0.70
    讓
    0.68
    drums
    0.66
     ವಿಶೇಷ
    0.65
     Anthem
    0.65
     crappy
    0.65
     सर्वश्रेष्ठ
    0.64
    POSITIVE LOGITS
     Debt
    0.82
     retirement
    0.73
     deb
    0.72
    رفته
    0.72
     debt
    0.71
     Deb
    0.69
    volved
    0.68
     Ouvrard
    0.67
    deb
    0.66
    ტ
    0.64
    Activations Density 0.002%

    No Known Activations