© 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. 51572
    Prev
    Next
    INDEX
    Explanations

    phrases like "a couple" or "party in"

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

    OpenAI leading AI company

    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
    પ
    0.55
    t
    0.53
    City
    0.50
    beat
    0.49
    Colonel
    0.49
    oblot
    0.49
     ரசிகர்கள்
    0.49
    č
    0.49
    city
    0.48
    Norway
    0.48
    POSITIVE LOGITS
     viviendas
    0.45
     microbiological
    0.44
     diversa
    0.43
     uterine
    0.42
     euh
    0.42
     Includes
    0.41
     mismas
    0.41
     phụ
    0.41
    时间和
    0.41
     includes
    0.41
    Activations Density 0.000%

    No Known Activations