© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42576
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RequestHandler
    0.45
    ()],
    0.42
    Gulf
    0.41
     Eurasian
    0.40
     VM
    0.40
    VM
    0.40
     crossbow
    0.40
    Medieval
    0.39
     zadr
    0.39
     همد
    0.39
    POSITIVE LOGITS
    磅
    0.43
     plaza
    0.42
    साइट
    0.41
    广场
    0.41
     plazas
    0.41
    当前
    0.40
     rubble
    0.40
     programmer
    0.39
     onsite
    0.39
    股
    0.39
    Activations Density 0.030%

    No Known Activations