© 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. 15342
    Prev
    Next
    INDEX
    Explanations

    turn: Issuer: whom are

    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
     Один
    1.03
     aspects
    0.96
    焘
    0.96
     energetics
    0.93
    {}",
    0.93
     である
    0.92
    ার
    0.91
     принятия
    0.91
     入れ
    0.90
     Rift
    0.90
    POSITIVE LOGITS
    hadow
    1.21
    
    1.10
    zzles
    1.05
     giọng
    1.03
    
    1.03
    ре
    1.03
    
    1.01
    empre
    1.01
     DevOps
    1.01
    ců
    0.99
    Activations Density 0.000%

    No Known Activations