© 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. 76819
    Prev
    Next
    INDEX
    Explanations

    label after colon, medical terms, spokesman for

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

    quarter, port, resource, likely, shimmering

    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
    s
    0.57
     Minister
    0.50
     Ministry
    0.50
    ၞ
    0.50
    sion
    0.49
     behind
    0.48
    ังสือ
    0.48
     squid
    0.47
    ا
    0.47
    ς
    0.46
    POSITIVE LOGITS
     وذلك
    0.48
    embros
    0.48
    hingga
    0.47
     այ
    0.46
    લા
    0.45
    ">−</
    0.45
    -+
    0.44
    égal
    0.44
     સમા
    0.43
     नाभ
    0.43
    Activations Density 0.000%

    No Known Activations