© 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. 251455
    Prev
    Next
    INDEX
    Explanations

    titles, variety, web, roofing

    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
     Figura
    0.51
     eyewear
    0.50
     feminine
    0.45
     Hid
    0.45
    ového
    0.45
    '
    0.45
     Carav
    0.44
     eyed
    0.44
    avax
    0.44
     darkened
    0.43
    POSITIVE LOGITS
     রাম
    0.51
     계속
    0.47
     gửi
    0.46
    繼續
    0.46
     많이
    0.46
     빠
    0.46
     পড়বে
    0.45
    䔉
    0.45
     继续
    0.44
    變
    0.44
    Activations Density 0.001%

    No Known Activations