© 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. 122961
    Prev
    Next
    INDEX
    Explanations

    lot of bundles

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

    { like } curly braces with commands

    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
     necesariamente
    0.60
     investigação
    0.56
    ᱼ
    0.55
     ámbitos
    0.54
     হোমিও
    0.54
    ᒃ
    0.54
     desarroll
    0.53
     இட
    0.53
     biología
    0.53
     estoy
    0.52
    POSITIVE LOGITS
    !
    0.52
    ,
    0.51
    hf
    0.50
     i
    0.50
     $
    0.48
     t
    0.47
    0.46
    lp
    0.43
    },
    0.43
     Horizon
    0.43
    Activations Density 0.001%

    No Known Activations