© 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-16K
    7. 12512
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    countries and services

    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_16k_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
    Klik
    0.46
    ข
    0.46
    云南
    0.46
     Пер
    0.45
    Prothorax
    0.45
     त्रिपुरा
    0.45
    ğ
    0.45
    ꞎ
    0.45
    Pyrimidine
    0.44
    ⺌
    0.44
    POSITIVE LOGITS
     Debbie
    0.40
     Emeritus
    0.37
     fee
    0.37
     donate
    0.36
     stockholders
    0.36
     athletes
    0.35
     Phyt
    0.35
     OJ
    0.35
     try
    0.35
     contracts
    0.35
    Activations Density 0.159%

    No Known Activations