© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18287
    Prev
    Next
    INDEX
    Explanations

    my ownmy originalmy creationsmy update

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

    GF or punctuation

    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
    鉑
    0.47
    রাজের
    0.47
    皰
    0.47
     élections
    0.46
     Mink
    0.46
     intenz
    0.46
     Eugène
    0.45
    苯
    0.45
    運
    0.45
    =’
    0.44
    POSITIVE LOGITS
    tsy
    0.50
    pt
    0.48
    ्तीय
    0.48
    spired
    0.46
    servic
    0.46
    collider
    0.46
     ample
    0.45
    してます
    0.45
    uirre
    0.44
    प्ली
    0.44
    Activations Density 0.000%

    No Known Activations