© 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. 89020
    Prev
    Next
    INDEX
    Explanations

    reasonable efforts, using yeast

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

    work, material, rooms, and free

    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
    <eos>
    0.48
    iary
    0.47
    ↵↵
    0.46
    No
    0.44
    ↵↵↵
    0.43
     dictates
    0.42
     liable
    0.42
    一系列
    0.41
     DEPARTMENT
    0.41
     зона
    0.40
    POSITIVE LOGITS
     sechs
    0.52
     bygg
    0.52
    ക്കുറിച്ച
    0.52
     forskj
    0.50
     ១
    0.50
     hike
    0.49
     resTmp
    0.48
     trenger
    0.48
     betyd
    0.48
     frauen
    0.48
    Activations Density 0.000%

    No Known Activations