© 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. 11007
    Prev
    Next
    INDEX
    Explanations

    mentioned words, phrases, or terms

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

    mentioning or defining concepts

    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
     আনুশকা
    0.42
    7
    0.42
     capítulo
    0.40
     đây
    0.40
     시작하겠습니다
    0.40
     orta
    0.39
     spune
    0.39
    acağız
    0.39
    Trung
    0.39
    ﮨ
    0.39
    POSITIVE LOGITS
     مذکور
    1.10
     aforesaid
    0.73
     of
    0.73
     aforementioned
    0.66
     mentioned
    0.64
    ดังกล่าว
    0.61
     tersebut
    0.59
    上述
    0.59
     mencionado
    0.59
     उक्त
    0.55
    Activations Density 0.069%

    No Known Activations