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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7532
    Prev
    Next
    INDEX
    Explanations

    art, games, food descriptions

    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
     other
    1.06
     ilang
    1.00
    paces
    0.98
    پلز
    0.95
    ⓪
    0.95
     Осо
    0.94
    ome
    0.93
     sonra
    0.93
     Este
    0.92
    hee
    0.91
    POSITIVE LOGITS
    isierte
    0.92
    iskt
    0.88
    শিপ
    0.88
     roomy
    0.87
    श
    0.87
    жный
    0.87
     Dorchester
    0.87
    ροφο
    0.86
    uated
    0.86
    isasi
    0.86
    Activations Density 0.052%

    No Known Activations