© 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. 121187
    Prev
    Next
    INDEX
    Explanations

    government, choose, share, pick

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

    for or file

    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
    ي
    0.58
    t
    0.55
    i
    0.53
    r
    0.51
    l
    0.48
     Ecke
    0.47
    ி
    0.46
    p
    0.46
     opinion
    0.45
     side
    0.44
    POSITIVE LOGITS
    origData
    0.56
     συγκεκρι
    0.55
     karşılaş
    0.50
     계약
    0.49
     নিজ
    0.48
    Domic
    0.47
     दट
    0.47
    Issledovatel
    0.47
    Tareas
    0.46
    quée
    0.46
    Activations Density 0.001%

    No Known Activations