© 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. 80469
    Prev
    Next
    INDEX
    Explanations

    Rockefeller Foundation and Carrier accepts

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

    I appreciate

    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
    Wool
    0.52
    Nov
    0.49
    ousand
    0.48
    Cz
    0.47
    Fear
    0.46
    倛
    0.46
    NumberOf
    0.46
    Horn
    0.46
    瞍
    0.45
    Leon
    0.45
    POSITIVE LOGITS
     annotation
    0.46
     docket
    0.45
     stricter
    0.45
     transmits
    0.45
     itinerary
    0.43
     grammar
    0.42
     broadcaster
    0.42
     literary
    0.42
     bulletin
    0.41
     subcellular
    0.41
    Activations Density 0.001%

    No Known Activations