© 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. 237105
    Prev
    Next
    INDEX
    Explanations

    listing charities and causes

    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
     case
    0.50
    0.49
    compare
    0.49
     kan
    0.48
     review
    0.47
     三
    0.46
    ेंगे
    0.46
     ?
    0.46
     定义
    0.46
     thoại
    0.45
    POSITIVE LOGITS
     Obispo
    0.51
     Cabe
    0.50
     Entrenamiento
    0.47
    განიზ
    0.47
    ბ
    0.46
     Wetter
    0.46
    تن
    0.46
     Alber
    0.45
     Vestone
    0.45
     descubrimiento
    0.45
    Activations Density 0.001%

    No Known Activations