© 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. 151077
    Prev
    Next
    INDEX
    Explanations

    specific nouns after common words

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

    words like "Patpong" or languages like "German"

    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
    bouw
    0.53
    H
    0.50
    علی
    0.47
     ചൂ
    0.47
     ඉද
    0.46
    বাদী
    0.43
    στημα
    0.43
    film
    0.43
    avacan
    0.42
    ɱ
    0.42
    POSITIVE LOGITS
    준다
    0.48
     reino
    0.45
     matrices
    0.44
     patrón
    0.43
     printer
    0.43
    Firstly
    0.42
     micrographs
    0.42
     transvers
    0.42
     diagonals
    0.42
     canola
    0.42
    Activations Density 0.002%

    No Known Activations