© 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. 222287
    Prev
    Next
    INDEX
    Explanations

    integration or datasets

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

    Johannesburg's origin, Geology

    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
     refrigerator
    0.42
    t
    0.42
     lös
    0.39
     \
    0.39
    ạp
    0.39
     Morley
    0.39
    theit
    0.39
    いたい
    0.38
    ecia
    0.38
    婭
    0.38
    POSITIVE LOGITS
    샷
    0.54
     બંને
    0.50
    INFRINGEMENT
    0.50
    금융
    0.47
    จึง
    0.47
    บอล
    0.47
     richesse
    0.46
     КП
    0.46
    ος
    0.45
    eper
    0.45
    Activations Density 0.000%

    No Known Activations