© 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. 62096
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    Hello, Alice!

    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
     Twilight
    0.40
     বেশী
    0.39
     Challenger
    0.38
    রাও
    0.38
    数列
    0.38
    Twilight
    0.37
    
    0.36
     동일
    0.36
    များနှင့်
    0.36
    疋
    0.36
    POSITIVE LOGITS
     bilmi
    0.45
    ECK
    0.43
     escritura
    0.40
    CAPE
    0.40
     minha
    0.40
     yerden
    0.40
     vagy
    0.38
     tecla
    0.38
     қай
    0.38
    FIELDS
    0.38
    Activations Density 0.000%

    No Known Activations