© 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. 148749
    Prev
    Next
    INDEX
    Explanations

    speaking one's mind

    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
    ζί
    0.86
     zv
    0.78
    pat
    0.74
    ّة
    0.72
    path
    0.70
    роб
    0.70
    టి
    0.69
    冏
    0.68
    θεση
    0.68
    jira
    0.68
    POSITIVE LOGITS
    کي
    0.75
     স্ত্র
    0.71
    ombres
    0.71
     consigui
    0.71
     pitching
    0.70
    insulated
    0.69
    窯
    0.68
     Key
    0.68
     impermeable
    0.68
     सीएम
    0.67
    Activations Density 0.000%

    No Known Activations