© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193358
    Prev
    Next
    INDEX
    Explanations

    proportional donation supplier patches

    np_acts-logits-general · gemini-2.5-flash-lite

    measurable and concluding concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    데이
    0.49
    혐
    0.48
    켠
    0.48
    Ķ
    0.47
    प
    0.46
    Customize
    0.46
    బా
    0.46
    getActive
    0.44
    लेख
    0.44
    Câu
    0.44
    POSITIVE LOGITS
     ထ
    0.55
    te
    0.55
     hippocampus
    0.49
    otur
    0.48
     পড়ার
    0.47
     নির্ভর
    0.46
     optomet
    0.44
     സീ
    0.44
    zach
    0.43
     volutpat
    0.43
    Activations Density 0.000%

    No Known Activations