© 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. 126097
    Prev
    Next
    INDEX
    Explanations

    history and context

    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
    <0xE1>
    0.59
    ret
    0.51
    æ
    0.50
    yt
    0.50
    assy
    0.48
    s
    0.47
    AI
    0.47
    ulture
    0.47
    look
    0.46
    iri
    0.46
    POSITIVE LOGITS
    푐
    0.57
    ोष
    0.55
     ofthe
    0.55
     canes
    0.54
    인은
    0.54
     despl
    0.53
    ляются
    0.52
    乆
    0.52
    лении
    0.52
    imètre
    0.52
    Activations Density 0.000%

    No Known Activations