© 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. 148998
    Prev
    Next
    INDEX
    Explanations

    until all

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

    starting phrase "so,"

    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
     seleccionar
    0.49
     ex
    0.47
     ක්ර
    0.46
     แน
    0.46
    的应用
    0.44
     LOTRAchievement
    0.44
     プリント
    0.44
     e
    0.44
     AK
    0.44
    ancellor
    0.43
    POSITIVE LOGITS
    راً
    0.44
    seeds
    0.44
    準備
    0.43
    rawy
    0.43
    discord
    0.43
    romet
    0.42
    हु
    0.41
    人民
    0.41
    decay
    0.41
    homes
    0.41
    Activations Density 0.000%

    No Known Activations