© 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. 249454
    Prev
    Next
    INDEX
    Explanations

    then nominating administrators know all over

    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
     ВО
    0.61
     МО
    0.58
     descansar
    0.52
     চৈতন্যের
    0.50
    бто
    0.49
    大切な
    0.49
    🐲
    0.48
     КО
    0.48
     Notas
    0.47
    ᇁ
    0.46
    POSITIVE LOGITS
    nem
    0.63
    rung
    0.58
    lent
    0.57
    s
    0.55
    g
    0.55
    nent
    0.54
    lau
    0.54
    law
    0.52
    i
    0.52
    lama
    0.51
    Activations Density 0.001%

    No Known Activations