© 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. 148337
    Prev
    Next
    INDEX
    Explanations

    boxer, Port Chester, barbers, exhibition

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

    pursue, buy, answer, needs, acquisitions, pain

    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
    井
    0.47
    정
    0.45
    جه
    0.44
    ون
    0.44
    账
    0.43
     vanno
    0.43
    پ
    0.43
    探
    0.43
    تقدم
    0.42
     chron
    0.42
    POSITIVE LOGITS
     இந்நிலையில்
    0.53
     destabil
    0.49
     പക്ഷേ
    0.48
     оформ
    0.48
     ஆனால்
    0.48
    neutral
    0.46
    andaş
    0.45
     ลด
    0.45
     FOM
    0.44
     শিক্ষার
    0.44
    Activations Density 0.000%

    No Known Activations