© 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. 34449
    Prev
    Next
    INDEX
    Explanations

    Black Rock Desert

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

    introduction to lists or topics

    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
    ,
    0.49
     Res
    0.48
    h
    0.46
    Res
    0.46
    K
    0.46
    ，
    0.45
    .
    0.44
    ArrayList
    0.44
    J
    0.44
    ltimes
    0.43
    POSITIVE LOGITS
     Ngày
    0.58
     বন্যা
    0.54
     selben
    0.54
     ദുൽ
    0.54
     Xét
    0.54
    ेंगू
    0.53
    ্ী
    0.53
    linkOpacity
    0.53
    ຢ່າງ
    0.52
     crocodiles
    0.52
    Activations Density 0.000%

    No Known Activations