© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11768
    Prev
    Next
    INDEX
    Explanations

    numbers and phone numbers

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

    identifying specific events or terms

    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
    一款
    0.49
    辞
    0.49
     Е
    0.49
    료
    0.48
     potuto
    0.48
     kunst
    0.46
     Erek
    0.46
    域
    0.46
     Municipio
    0.46
     Section
    0.45
    POSITIVE LOGITS
    unningham
    0.52
     العامل
    0.45
     as
    0.45
    торами
    0.44
     engineers
    0.44
    গ্রাম
    0.44
    ateurs
    0.44
    tham
    0.44
     স্বেচ্ছাসেব
    0.43
     unseren
    0.42
    Activations Density 0.000%

    No Known Activations