© 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. 219211
    Prev
    Next
    INDEX
    Explanations

    educational or business contexts

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

    disclaimers and notes

    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
    ভিয়েতনাম
    0.47
    ленном
    0.46
     tabindex
    0.45
    内在
    0.45
    приклад
    0.44
     inheriting
    0.44
    佼
    0.44
    rène
    0.43
    జేపీ
    0.43
    ního
    0.43
    POSITIVE LOGITS
     Kees
    0.56
     l
    0.55
     ﺍﻟ
    0.53
     coronavirus
    0.52
     azot
    0.48
     Ass
    0.48
     cependant
    0.47
     עצ
    0.47
     ل
    0.47
     ۲
    0.47
    Activations Density 0.000%

    No Known Activations