© 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. 137663
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    lists of items or sequential data

    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
    好
    0.50
    ავს
    0.48
    Elegant
    0.47
    上がる
    0.46
    λαν
    0.45
    াতাড়ি
    0.44
    л
    0.44
    시키
    0.43
    ვნ
    0.43
    ვენ
    0.43
    POSITIVE LOGITS
     jedoch
    0.53
     intuitively
    0.50
     intuit
    0.50
     mêmes
    0.48
     シュ
    0.48
     uma
    0.48
     Toutefois
    0.47
     nœ
    0.47
     Omnibus
    0.47
     têm
    0.47
    Activations Density 0.000%

    No Known Activations