© 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. 98050
    Prev
    Next
    INDEX
    Explanations

    former/latter brand or half

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

    only emojis

    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
     العالم
    0.54
     अनाउंस
    0.53
     عجیب
    0.53
    undaki
    0.53
    umumkan
    0.51
     Бүгенге
    0.50
     Prozent
    0.49
    惀
    0.49
    駋
    0.48
    anjutan
    0.48
    POSITIVE LOGITS
     fiber
    0.55
     valves
    0.54
     shellfish
    0.54
     accessories
    0.52
     valve
    0.52
     conveyors
    0.52
     fibers
    0.51
     raspberry
    0.51
     connectors
    0.51
     raspberries
    0.51
    Activations Density 0.003%

    No Known Activations