© 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. 217516
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

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

    dequeue, pop, shift operations with ()

    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
    app
    0.61
    ust
    0.59
    ST
    0.59
    ada
    0.58
    am
    0.57
    p
    0.57
    in
    0.55
    align
    0.55
    AP
    0.54
    saya
    0.54
    POSITIVE LOGITS
    ،
    0.46
     Chry
    0.45
     النص
    0.45
     rejet
    0.45
    ၊
    0.45
     Colle
    0.45
     Cyrus
    0.44
     keyValue
    0.44
     queryObject
    0.44
     مؤ
    0.43
    Activations Density 0.000%

    No Known Activations