© 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-16K
    7. 171
    Prev
    Next
    INDEX
    Explanations

    game turn markers

    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_16k_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
    <0x80>
    0.40
    ️
    0.37
    ed
    0.34
    swering
    0.33
    ’
    0.32
    ly
    0.32
    '
    0.31
    ून
    0.31
     οποία
    0.31
     though
    0.31
    POSITIVE LOGITS
    DanhMuc
    0.41
    vadipine
    0.39
    gué
    0.36
    örungen
    0.36
    кугӀ
    0.35
    Deutsch
    0.35
    राबरी
    0.34
    ethash
    0.34
     rejet
    0.34
    cargar
    0.34
    Activations Density 4.921%

    No Known Activations