© 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. 135119
    Prev
    Next
    INDEX
    Explanations

    you can try

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

    disaster, risk, and ethical concepts

    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
    asibility
    0.41
    winged
    0.40
    AWS
    0.39
     primordial
    0.39
    む
    0.39
    dern
    0.39
    ྣ
    0.38
    荊
    0.38
    POSIX
    0.38
    starter
    0.38
    POSITIVE LOGITS
     Piccolo
    0.57
     Reno
    0.55
     extérieures
    0.52
     théorie
    0.51
     Projet
    0.50
     économiques
    0.50
     tăng
    0.50
     Pico
    0.50
     giảm
    0.49
     Profit
    0.49
    Activations Density 0.001%

    No Known Activations