© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    state of existence

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

    fragmentary evidence documented

    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
     потрібно
    0.80
     इंसान
    0.75
    Choisissez
    0.73
    Nuestro
    0.66
    Чтобы
    0.66
     Гуляць
    0.65
    ￳
    0.65
    Jeśli
    0.64
     garantías
    0.64
    ్ఞ
    0.64
    POSITIVE LOGITS
     fragmentary
    0.90
     extant
    0.84
     holotype
    0.81
     occasional
    0.79
     putative
    0.78
     probably
    0.77
     apparently
    0.77
     unpublished
    0.75
     stratigraphic
    0.74
     S
    0.73
    Activations Density 0.147%

    No Known Activations