© 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. 69357
    Prev
    Next
    INDEX
    Explanations

    contracts and futures

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

    list/tuple structures

    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
    ↵↵↵↵
    0.42
     ساتھ
    0.39
    بری
    0.39
     Garza
    0.39
    ↵↵↵↵↵
    0.38
     coinage
    0.37
     attenuated
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
     together
    0.36
    POSITIVE LOGITS
     вновь
    0.45
     второго
    0.42
     हिंदू
    0.40
     अग्रवाल
    0.39
     बत्रा
    0.39
     формирование
    0.39
    Mapping
    0.38
     errorMessage
    0.38
    cdc
    0.38
     формування
    0.38
    Activations Density 0.001%

    No Known Activations