© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7166
    Prev
    Next
    INDEX
    Explanations

    timestamps in json

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

    machine-formatted tokens—especially URLs and date/time strings—often appearing inside code or structured technical examples.

    oai_token-act-pair · gpt-5Triggered 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
     আর
    0.17
     giữa
    0.17
     mesons
    0.17
    gheatmap
    0.16
    :
    0.16
     planer
    0.16
     nền
    0.16
    xcuserdata
    0.16
     منجر
    0.16
     shrubs
    0.16
    POSITIVE LOGITS
    ும்
    0.22
     tohoto
    0.21
     എന്നിവ
    0.21
    ų
    0.20
     ۵
    0.20
    ს
    0.20
    ۶
    0.20
     ۶
    0.19
    ę
    0.19
     cierto
    0.19
    Activations Density 3.087%

    No Known Activations