© 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. 10739
    Prev
    Next
    INDEX
    Explanations

    what the question is

    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
    א
    1.48
    Пи
    1.45
    伡
    1.38
    ০
    1.38
    ри
    1.34
     अणुओं
    1.34
    žené
    1.32
    崬
    1.32
    Ар
    1.31
    ي
    1.31
    POSITIVE LOGITS
     shaken
    1.05
    scapes
    1.01
     unspoken
    0.98
    credibly
    0.96
     stubbornly
    0.95
    teenth
    0.94
     frightening
    0.94
    billy
    0.93
     ferocious
    0.92
     bitten
    0.92
    Activations Density 0.001%

    No Known Activations