© 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. 6317
    Prev
    Next
    INDEX
    Explanations

    technical and domain-specific vocabulary

    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
    <bbox>
    0.85
    intégr
    0.76
    :"",
    0.75
    icosa
    0.74
     अद्भ
    0.72
     holographic
    0.69
    參数
    0.69
    =?,
    0.69
    參數
    0.69
    初始
    0.68
    POSITIVE LOGITS
     Crab
    0.81
     crab
    0.76
    <start_of_image>
    0.74
    ようだ
    0.74
     Westchester
    0.73
     senior
    0.73
     comedor
    0.72
     Cleveland
    0.72
     Chinatown
    0.70
    ണിത്
    0.70
    Activations Density 0.571%

    No Known Activations