© 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. 12359
    Prev
    Next
    INDEX
    Explanations

    consumer options

    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
     premature
    0.46
     tariff
    0.41
     reproduc
    0.41
     accion
    0.41
    ະພັນ
    0.41
     programmatic
    0.40
    <0x80>
    0.39
     thành
    0.39
     pipeline
    0.39
     process
    0.38
    POSITIVE LOGITS
     ຮ
    0.49
    nicki
    0.48
    
    0.47
     கல்லற
    0.47
    ܪ
    0.45
     ฮ
    0.45
    ycling
    0.45
    瑪
    0.44
    Bella
    0.44
    ilus
    0.44
    Activations Density 0.002%

    No Known Activations