© 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. 116861
    Prev
    Next
    INDEX
    Explanations

    image source

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

    "Uber", "film", "letters", "components"

    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
     રાજ્ય
    0.49
     পর্যবেক্ষণ
    0.43
    Custodian
    0.43
     샤
    0.43
     conjugation
    0.43
    ጣም
    0.42
    Forgery
    0.42
     vontade
    0.42
     кой
    0.42
     মার
    0.42
    POSITIVE LOGITS
    an
    0.52
     unwittingly
    0.50
     innov
    0.49
    ان
    0.49
    h
    0.46
    in
    0.44
     instinctively
    0.44
    аст
    0.44
     ambul
    0.44
     Innovative
    0.43
    Activations Density 0.000%

    No Known Activations