© 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. 6917
    Prev
    Next
    INDEX
    Explanations

    languages for 'and'

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

    and in other languages

    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
    গ্রামে
    0.36
     ہو۔
    0.35
     گئی۔
    0.34
     plays
    0.33
     ہیں۔
    0.33
    ത്തിയത്
    0.32
     ہوں۔
    0.32
    %；
    0.32
     kullanımı
    0.31
     hanging
    0.31
    POSITIVE LOGITS
     และ
    0.89
     आणि
    0.88
     અને
    0.88
     ਅਤੇ
    0.86
     এবং
    0.86
     và
    0.79
     और
    0.79
     and
    0.76
     ಮತ್ತು
    0.75
     και
    0.72
    Activations Density 0.352%

    No Known Activations