© 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. 6512
    Prev
    Next
    INDEX
    Explanations

    encodings beyond English

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

    Tokens that occur in the assistant's long, informative explanatory prose (model-generated explanatory or descriptive sentences).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Lice
    0.20
    蓣
    0.20
     때는
    0.19
     Enum
    0.19
     Copper
    0.19
     Lucifer
    0.19
     Metal
    0.19
    かもしれませんが
    0.18
     Afternoon
    0.18
    ますが
    0.18
    POSITIVE LOGITS
    е
    0.24
    А
    0.24
     सुमारे
    0.22
    ൈ
    0.22
    ۔
    0.21
    ३
    0.21
    ሉ።
    0.21
     і
    0.20
    за
    0.20
    ای
    0.20
    Activations Density 1.250%

    No Known Activations