© 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. 203781
    Prev
    Next
    INDEX
    Explanations

    difficult spontaneous spontaneous

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

    scaling of models and parameters

    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
    uiscono
    0.56
     ܥ
    0.50
     Україні
    0.47
    ȟ
    0.47
    ባት
    0.46
     見
    0.45
    िफिकेट
    0.45
    acées
    0.45
    COLORS
    0.44
    פּ
    0.44
    POSITIVE LOGITS
     sceptical
    0.46
    かもしれませんが
    0.46
     diffuse
    0.45
     dificult
    0.44
     spontaneous
    0.43
     colleague
    0.43
    馔
    0.43
    elasticsearch
    0.43
     esche
    0.43
     difficult
    0.42
    Activations Density 0.000%

    No Known Activations