© 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. 54814
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    efficiency and conciseness

    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
    timelist
    0.48
     autocl
    0.46
     sarcastic
    0.46
     گیا۔
    0.43
     Яндекс
    0.43
     lysates
    0.43
     Ministerio
    0.42
    ޞ
    0.42
    ສຸດ
    0.42
     minister
    0.42
    POSITIVE LOGITS
    ürk
    0.55
     sün
    0.47
    üm
    0.47
    igan
    0.45
    ického
    0.45
    iena
    0.45
    nya
    0.44
    älle
    0.44
     joka
    0.44
    akyat
    0.44
    Activations Density 0.001%

    No Known Activations