© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6716
    Prev
    Next
    INDEX
    Explanations

    analysis and classification methods

    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
    лу
    1.20
    𝚂
    1.18
     Дру
    1.17
    િય
    1.15
    
    1.14
     compromised
    1.11
    ᴙ
    1.09
     grove
    1.06
     sustained
    1.02
    ſed
    1.02
    POSITIVE LOGITS
    يال
    0.96
    ัง
    0.95
    processes
    0.94
    적
    0.90
    植物
    0.88
    der
    0.87
    i
    0.87
    享
    0.85
    decision
    0.85
    방
    0.84
    Activations Density 0.218%

    No Known Activations