© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199298
    Prev
    Next
    INDEX
    Explanations

    replacing or tuning out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ആദ്യ
    0.55
    我们在
    0.46
    醿
    0.43
     Zaman
    0.40
    aktual
    0.40
     trakcie
    0.40
     Manuscripts
    0.40
     நேரம்
    0.39
    鋈
    0.39
     राइ
    0.39
    POSITIVE LOGITS
     pact
    0.50
     tuck
    0.48
     hemp
    0.48
     merger
    0.48
     velcro
    0.47
     mezz
    0.47
     treaty
    0.46
    )",
    0.46
     vending
    0.46
     poll
    0.46
    Activations Density 0.008%

    No Known Activations