© 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. 14008
    Prev
    Next
    INDEX
    Explanations

    brands and specific entities

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

    no single entity

    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
    គ
    0.47
     piety
    0.46
     grievous
    0.42
     newdata
    0.41
     minuta
    0.41
    ORUS
    0.40
    ํ
    0.40
     त
    0.40
    े
    0.39
     secretions
    0.39
    POSITIVE LOGITS
     Roblox
    0.42
     카
    0.41
     Snapchat
    0.41
    🛣
    0.41
     HubSpot
    0.40
     Chipotle
    0.40
     Fortnite
    0.39
    టర్‌
    0.39
     পরিষেবা
    0.39
     Coachella
    0.38
    Activations Density 0.169%

    No Known Activations