© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10703
    Prev
    Next
    INDEX
    Explanations

    multi-language punctuation

    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_9_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
    স
    1.11
    စိတ်အပိုင်း
    0.95
    𝐬
    0.85
    ɳ
    0.73
     spus
    0.72
    ました
    0.72
    ϲ
    0.70
    dır
    0.70
    Ꮑ
    0.70
    ته
    0.70
    POSITIVE LOGITS
    ところ
    0.82
    ifrån
    0.76
    timelist
    0.76
    个月
    0.74
     emphatically
    0.71
    smanship
    0.70
    ногда
    0.70
     transversely
    0.70
    박
    0.70
     vigour
    0.69
    Activations Density 0.014%

    No Known Activations