© 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. 42576
    Prev
    Next
    INDEX
    Explanations

    temple courtyard plaza artefacts

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

    ancient ruins and archaeological sites

    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
    stedt
    0.40
    ਕੇ
    0.39
     zadr
    0.39
    蜻
    0.39
    RequestHandler
    0.39
    fé
    0.38
     Genealogy
    0.38
    Петербург
    0.38
     Prussia
    0.38
    Deferred
    0.38
    POSITIVE LOGITS
    广场
    0.47
    밋
    0.47
    磅
    0.44
     rubble
    0.43
     plazas
    0.43
     组件
    0.42
    畝
    0.42
     plaza
    0.41
    blocks
    0.41
    场地
    0.40
    Activations Density 0.056%

    No Known Activations