© 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. 86779
    Prev
    Next
    INDEX
    Explanations

    carbon derived, consideration, network analysis, substitute

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

    rain and atmosphere

    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
    ش
    0.57
    ש
    0.57
    质量
    0.53
    ა
    0.53
    ř
    0.53
    pletely
    0.52
    ت
    0.50
    矫
    0.50
    Pe
    0.50
    ędzie
    0.50
    POSITIVE LOGITS
     accompany
    0.44
     asparagus
    0.43
     artillery
    0.43
     ireo
    0.43
     insurgents
    0.42
     dusk
    0.41
     withd
    0.41
     rains
    0.41
     zig
    0.41
     avoid
    0.41
    Activations Density 0.000%

    No Known Activations