© 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. 13743
    Prev
    Next
    INDEX
    Explanations

    sentence start after punctuation

    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
     समस्या
    0.89
    У
    0.80
    운
    0.80
    Problem
    0.78
    Стро
    0.77
    ※
    0.76
    較
    0.76
    Patch
    0.75
     ব্যায়াম
    0.75
    훅
    0.74
    POSITIVE LOGITS
    ₂,
    1.05
    perin
    1.00
    erdere
    1.00
    anwhile
    0.96
    ispielsweise
    0.96
    ákat
    0.96
    etah
    0.95
    alada
    0.95
    наче
    0.94
    槊
    0.94
    Activations Density 0.004%

    No Known Activations