© 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. 146357
    Prev
    Next
    INDEX
    Explanations

    animals, Europe, application

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

    legitimate, focus on

    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
     khủng
    0.50
     donné
    0.49
     oxidized
    0.49
    ឍ
    0.49
     oksid
    0.48
     করব
    0.48
     வாக
    0.46
     computations
    0.46
     boxShadow
    0.46
     экзем
    0.46
    POSITIVE LOGITS
    I
    0.47
     week
    0.45
    spring
    0.45
     अजीब
    0.41
    places
    0.41
     sumber
    0.39
     دوسروں
    0.39
     strange
    0.39
    Weekly
    0.39
     Thursday
    0.38
    Activations Density 0.002%

    No Known Activations