Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8076
    Prev
    Next
    INDEX
    Explanations

    academic journals and citations

    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
     sını
    0.92
    ﺮ
    0.90
     mellitus
    0.90
    提升
    0.89
     не
    0.88
    ountains
    0.84
    стойчи
    0.83
    ﻢ
    0.83
     التي
    0.83
    грани
    0.83
    POSITIVE LOGITS
     Verbrauch
    0.68
    क़
    0.67
     Contributions
    0.66
     Telegraph
    0.65
    Wax
    0.64
     Considering
    0.64
     Coming
    0.64
    č
    0.63
     Dieser
    0.63
    ാവ്
    0.62
    Activations Density 0.022%

    No Known Activations