© 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. 17-GEMMASCOPE-2-RES-16K
    7. 9748
    Prev
    Next
    INDEX
    Explanations

    html title tag

    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_17_width_16k_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
    횡
    1.04
     版本
    1.02
     થય
    0.97
     gjorde
    0.97
    ${
    0.97
     realizado
    0.92
    𝐭
    0.89
    又有
    0.88
     richt
    0.87
     अहि
    0.87
    POSITIVE LOGITS
     значений
    1.13
    怆
    1.03
    र
    1.02
    艨
    1.00
     lotions
    0.99
     eyewear
    0.97
     consumables
    0.96
    NgModule
    0.96
     Sunglasses
    0.95
    гло
    0.95
    Activations Density 0.009%

    No Known Activations