© 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. 29-GEMMASCOPE-2-RES-262K
    4. 149809
    Prev
    Next
    INDEX
    Explanations

    computational tasks and calculations

    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
    ãng
    0.81
    atiquement
    0.72
     whipping
    0.72
    uteurs
    0.70
    ዲስ
    0.70
    احث
    0.69
    缁
    0.68
     ಹುಡು
    0.67
     Prophets
    0.67
     pò
    0.67
    POSITIVE LOGITS
    ᒋ
    0.81
    Interrupt
    0.77
     incluem
    0.76
     pokrač
    0.75
    Recover
    0.75
    햅
    0.74
     που
    0.74
    FundMe
    0.73
     allClasses
    0.73
    kil
    0.72
    Activations Density 0.001%

    No Known Activations