© 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. 224011
    Prev
    Next
    INDEX
    Explanations

    organic produce

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

    very recognizable prominent famous

    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
    াতাড়ি
    0.52
    HCC
    0.46
    麹
    0.45
    competitive
    0.45
     ανάπτυ
    0.45
     καλύτε
    0.44
     cuant
    0.44
    itriangular
    0.43
     fcc
    0.43
     perone
    0.43
    POSITIVE LOGITS
    原
    0.46
     Oe
    0.45
    現實
    0.44
     રહ્યું
    0.44
     Recap
    0.43
     Franken
    0.43
     Wirklich
    0.43
     Visit
    0.43
     Peg
    0.42
     Wieder
    0.42
    Activations Density 0.001%

    No Known Activations