© 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. 12756
    Prev
    Next
    INDEX
    Explanations

    science behind

    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
     nice
    1.26
     bastante
    1.25
     nějak
    1.13
     fairly
    0.98
     😊
    0.98
     kinda
    0.98
     agak
    0.91
     somewhat
    0.91
     khá
    0.91
     decently
    0.90
    POSITIVE LOGITS
    全新的
    1.32
    全新
    1.27
    <unused497>
    1.13
     новий
    1.09
    本書
    1.05
     unrivalled
    1.04
     unprecedented
    1.03
    <unused337>
    1.03
    嶄
    1.02
     bestselling
    1.02
    Activations Density 0.048%

    No Known Activations