© 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. 52479
    Prev
    Next
    INDEX
    Explanations

    up to

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

    food, drink, and struggling

    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
    Prim
    0.50
    ्सा
    0.50
    貿
    0.49
    फ्त
    0.48
    Kir
    0.46
    ໂດຍ
    0.45
    হাম
    0.45
    нная
    0.45
    constructing
    0.44
    BRAND
    0.44
    POSITIVE LOGITS
     rar
    0.47
     haci
    0.46
     Gregorio
    0.46
     lept
    0.44
     tropes
    0.44
     .
    0.44
     Saccharomyces
    0.44
     Flüss
    0.43
     Sereth
    0.43
    eenth
    0.43
    Activations Density 0.000%

    No Known Activations