© 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. 131475
    Prev
    Next
    INDEX
    Explanations

    words like personal, fans, online, serious

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

    buying and refurbishing houses

    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
    دم
    0.50
    ج
    0.47
    C
    0.47
    ان
    0.46
    ‘
    0.46
    ین
    0.45
    CL
    0.44
     florals
    0.44
    ৫
    0.44
     ভারসাম
    0.44
    POSITIVE LOGITS
     dosen
    0.52
     odstr
    0.50
    ष्ट
    0.47
     빅뱅
    0.47
     sarkar
    0.46
     karte
    0.46
     Bakufu
    0.45
     muro
    0.45
     ngươi
    0.45
     hamstring
    0.45
    Activations Density 0.000%

    No Known Activations