© 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. 135353
    Prev
    Next
    INDEX
    Explanations

    only one or manufactured glass

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

    why cats do what they do

    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
    おすすめ
    0.49
     benefitting
    0.45
     স্বেচ্ছাসেব
    0.45
    iota
    0.44
    ።
    0.42
    फाइनल
    0.42
    იც
    0.42
    ლ
    0.41
     interfering
    0.40
    nucleon
    0.40
    POSITIVE LOGITS
     ölç
    0.48
     première
    0.48
     pengukuran
    0.48
     svojih
    0.48
     görev
    0.47
     varias
    0.45
     extré
    0.45
     várias
    0.44
     gire
    0.44
     aşağıdaki
    0.44
    Activations Density 0.000%

    No Known Activations