© 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. 95427
    Prev
    Next
    INDEX
    Explanations

    global products and cars

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

    Team Fortress 2 game contexts

    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
    Colonne
    0.51
    etat
    0.48
    اته
    0.48
     নিজেকে
    0.47
    Fetching
    0.46
    इ
    0.46
    lié
    0.45
    ור
    0.45
    alte
    0.45
    Jogador
    0.45
    POSITIVE LOGITS
     money
    0.46
     Premium
    0.44
     aftermarket
    0.44
     skins
    0.43
     OTA
    0.43
     intensity
    0.43
     for
    0.43
     B
    0.43
     festival
    0.43
     premium
    0.42
    Activations Density 0.001%

    No Known Activations