© 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. 126930
    Prev
    Next
    INDEX
    Explanations

    outcomes and conditions

    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
     Hội
    0.52
    ,
    0.47
     favourite
    0.46
     and
    0.45
     Day
    0.45
    起来
    0.45
     Lago
    0.45
     council
    0.45
     syllabus
    0.44
     şi
    0.43
    POSITIVE LOGITS
     використову
    0.50
     untersucht
    0.45
    딴
    0.44
    Фор
    0.43
    Warn
    0.42
     entdeckt
    0.42
    Stderr
    0.42
     mesurer
    0.41
    Bankr
    0.41
    MessageNow
    0.41
    Activations Density 0.006%

    No Known Activations