© 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. 52926
    Prev
    Next
    INDEX
    Explanations

    students learning, fiber cement, unequivocal commitment

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

    nature and art and teaching

    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
    {|\
    0.50
     足
    0.46
     იქნება
    0.46
     美国
    0.45
     システム
    0.45
    最新的
    0.45
    会自动
    0.45
    ्टी
    0.44
    会在
    0.44
     furthest
    0.44
    POSITIVE LOGITS
    elin
    0.47
     redox
    0.46
    varande
    0.46
    enne
    0.45
     പി
    0.44
    Request
    0.43
    ﺛ
    0.43
     be
    0.43
    itol
    0.43
    Release
    0.42
    Activations Density 0.000%

    No Known Activations