© 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. 52398
    Prev
    Next
    INDEX
    Explanations

    specific following words

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

    non-english characters or programming terms

    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
    a
    0.45
    விட்ட
    0.40
    쪽
    0.40
    这件事
    0.40
    getObject
    0.40
    있
    0.39
    research
    0.38
    の研究
    0.38
    searchResults
    0.38
    analytics
    0.37
    POSITIVE LOGITS
     grapefruit
    0.48
    
    0.47
     dhatu
    0.46
    मेस्टर
    0.46
     Fehler
    0.45
     bedtime
    0.44
     condensing
    0.43
    uties
    0.42
     SupCt
    0.41
    AlertType
    0.41
    Activations Density 0.000%

    No Known Activations