© 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. 161005
    Prev
    Next
    INDEX
    Explanations

    download materials for personal use

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

    flexible structures, programming keywords, costs, conditionals

    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
    す
    0.43
    стая
    0.42
    गील
    0.41
     పూర్తిగా
    0.41
    μία
    0.40
    🎉
    0.40
    洶
    0.39
     expectativas
    0.38
    email
    0.38
    زمین
    0.38
    POSITIVE LOGITS
     auftreten
    0.44
     दूंगा
    0.44
     gripe
    0.44
     promul
    0.43
    就是在
    0.43
     malle
    0.42
     고민
    0.41
     подрост
    0.41
    赸
    0.41
     NumericVector
    0.40
    Activations Density 0.001%

    No Known Activations