© 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. 38268
    Prev
    Next
    INDEX
    Explanations

    question number prefix

    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
    1
    0.49
    ad
    0.49
    AI
    0.48
    Input
    0.46
     Course
    0.46
    Ó
    0.46
    Type
    0.45
    Side
    0.44
    URA
    0.44
     T
    0.44
    POSITIVE LOGITS
     chromospheric
    0.54
    ណ្ត
    0.49
     dianggap
    0.49
     ayam
    0.48
     inviscid
    0.47
     blir
    0.47
     vanlig
    0.47
     beve
    0.47
    सेच
    0.47
     perut
    0.47
    Activations Density 0.002%

    No Known Activations