© 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. 194408
    Prev
    Next
    INDEX
    Explanations

    options, containment, significance

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

    iterative process, refinement

    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
    نتي
    0.59
    ائلة
    0.57
    ונ
    0.57
    <unused512>
    0.56
     苏
    0.55
     مرحبا
    0.55
     沈
    0.54
    <unused682>
    0.54
    鵬
    0.54
    <unused558>
    0.54
    POSITIVE LOGITS
     but
    0.51
     intending
    0.47
     hydrostatic
    0.47
     conness
    0.46
     tunnelling
    0.46
     actually
    0.45
     machining
    0.45
     ground
    0.45
     connex
    0.45
    meaning
    0.45
    Activations Density 0.001%

    No Known Activations