© 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. 36781
    Prev
    Next
    INDEX
    Explanations

    legal or trademark statements

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

    meaning isn't pre-ordained

    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
    '
    0.65
    ’
    0.52
    /
    0.50
     suit
    0.48
    '=
    0.45
     cani
    0.45
     suited
    0.45
     prese
    0.45
     harb
    0.45
    軽量
    0.45
    POSITIVE LOGITS
    ﺭ
    0.53
     केन्द्र
    0.50
    ंकी
    0.46
     записа
    0.45
    कार्
    0.45
    循环
    0.45
     ನನ್ನ
    0.45
     উন্নতি
    0.45
     మార
    0.45
    larında
    0.44
    Activations Density 0.000%

    No Known Activations