© 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. 36361
    Prev
    Next
    INDEX
    Explanations

    Wilson, Dub, Kaye, Smoky, Brighton

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

    Country, Age, Local

    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
    environment
    0.57
     と
    0.56
    ي
    0.55
    х
    0.55
    }+\
    0.54
    }+
    0.54
     ambiental
    0.53
    waitUntil
    0.53
     能力
    0.52
    environmental
    0.52
    POSITIVE LOGITS
    ﻊ
    0.50
    اصل
    0.50
    ighton
    0.48
     Kaye
    0.48
    ا
    0.46
    ESSION
    0.46
     Smoky
    0.46
    esta
    0.45
    ların
    0.45
     crude
    0.45
    Activations Density 0.002%

    No Known Activations