© 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. 117051
    Prev
    Next
    INDEX
    Explanations

    obtain a restriction

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

    calculating distances or allowing processes

    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
     ପ
    0.65
     університету
    0.62
     університе
    0.51
     بير
    0.50
     മനുഷ്യ
    0.50
     partialX
    0.50
     குறித்த
    0.49
     ഉയർന്ന
    0.49
     ipotesi
    0.47
     ویئر
    0.46
    POSITIVE LOGITS
    ুধ
    0.48
     name
    0.44
    ड़ों
    0.43
     Saad
    0.41
     G
    0.41
    Kot
    0.39
     referee
    0.39
    ugen
    0.39
    GetMapping
    0.39
     Champagne
    0.39
    Activations Density 0.000%

    No Known Activations