© 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. 32409
    Prev
    Next
    INDEX
    Explanations

    events and traditions

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

    mix of activities and experiences

    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
    }\
    0.45
    hammad
    0.40
     OECD
    0.40
     beraten
    0.40
     −/−
    0.39
    }
    0.39
     കേസ
    0.38
     }\
    0.38
    yilda
    0.38
     >
    0.38
    POSITIVE LOGITS
     Highway
    0.46
     railroad
    0.46
     banquet
    0.45
     Exposition
    0.45
     Tradition
    0.44
     festivities
    0.44
     Banquet
    0.43
     traditionnelle
    0.42
    这条
    0.41
    Highway
    0.41
    Activations Density 0.000%

    No Known Activations