© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9107
    Prev
    Next
    INDEX
    Explanations

    Indeed.com

    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
    er
    3.08
    ك
    2.96
     inference
    2.96
     accede
    2.80
     evitando
    2.74
    с
    2.68
     ilə
    2.55
    Д
    2.54
     invit
    2.52
     iria
    2.52
    POSITIVE LOGITS
    lessly
    3.10
    ">/</
    2.87
    ually
    2.76
    ">+</
    2.69
    م
    2.62
    ない
    2.56
     UIColor
    2.47
    (('
    2.44
    केंसी
    2.40
    м
    2.36
    Activations Density 0.009%

    No Known Activations