© 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. 221799
    Prev
    Next
    INDEX
    Explanations

    various kinds of

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

    certain words "various" "several"

    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
     jeśli
    0.39
     থেকে
    0.38
    で
    0.37
     jeżeli
    0.34
     এছাড়া
    0.34
     για
    0.33
     żeby
    0.33
    ี
    0.32
     pokud
    0.32
     học
    0.32
    POSITIVE LOGITS
    様々な
    0.48
     различные
    0.44
     различных
    0.40
    さまざまな
    0.39
     exorbit
    0.39
     diversas
    0.38
    特別な
    0.38
    various
    0.38
     различни
    0.38
     ciertas
    0.37
    Activations Density 0.881%

    No Known Activations