© 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. 136086
    Prev
    Next
    INDEX
    Explanations

    corvette washing supply love skills realisation

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

    ideas about data

    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
    apadani
    0.46
     hipster
    0.44
    вена
    0.43
    esist
    0.43
     いたし
    0.42
    狷
    0.42
     Ella
    0.41
    𒈪
    0.41
     Belle
    0.41
     Pakistani
    0.40
    POSITIVE LOGITS
    不论
    0.47
     применя
    0.46
     hodnot
    0.46
     utilisé
    0.45
     проверя
    0.45
     ম্যাজিস্ট্রেট
    0.45
    forget
    0.44
     přev
    0.44
    挑选
    0.44
    archive
    0.44
    Activations Density 0.000%

    No Known Activations