© 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. 66394
    Prev
    Next
    INDEX
    Explanations

    executive housekeeping

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

    historical context or models

    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
     hiểm
    0.52
     Polskiej
    0.51
     ۱۰
    0.50
    ZIONE
    0.50
     //</
    0.50
     pagine
    0.49
     вда
    0.49
     آئ
    0.49
    𒋼
    0.49
     localVarAccept
    0.48
    POSITIVE LOGITS
     ratios
    0.49
     methods
    0.48
     systolic
    0.48
     factor
    0.48
     straight
    0.48
     scrot
    0.47
     cerebral
    0.47
     handheld
    0.47
     learnings
    0.47
     things
    0.47
    Activations Density 0.000%

    No Known Activations