© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4425
    Prev
    Next
    INDEX
    Explanations

    computer vision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    indungan
    0.89
    ∬
    0.84
    嚎
    0.82
    recorder
    0.81
    ="
    0.79
    Luc
    0.79
     conducting
    0.78
    upload
    0.78
    öffentlich
    0.78
     upp
    0.77
    POSITIVE LOGITS
    م
    0.94
    ピーク
    0.91
    త్రిక
    0.91
    м
    0.90
    CISE
    0.90
    dN
    0.89
    텁
    0.88
    من
    0.88
    dT
    0.88
    nement
    0.87
    Activations Density 0.052%

    No Known Activations