© 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. 111668
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    names starting with common prefixes

    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
     FTX
    0.45
    
    0.43
    Bonjour
    0.43
     headquartered
    0.41
    ଡ
    0.40
    位於
    0.40
     Omicron
    0.39
    位于
    0.39
     Spacious
    0.39
    顶级
    0.39
    POSITIVE LOGITS
     sober
    0.45
     heroic
    0.45
    hibit
    0.43
     ந
    0.43
     skeptic
    0.43
    ษฐ
    0.43
     skeptical
    0.43
     meek
    0.43
    ｱ
    0.42
     inscr
    0.42
    Activations Density 0.006%

    No Known Activations