© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134918
    Prev
    Next
    INDEX
    Explanations

    knowledge cutoff

    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_40_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
     Darth
    0.45
     #
    0.39
     don
    0.38
     purse
    0.38
     sky
    0.38
     memorabilia
    0.37
     '
    0.37
     dor
    0.37
    reat
    0.36
     Uber
    0.36
    POSITIVE LOGITS
     ABSORBED
    0.42
     dechlorination
    0.40
    剽
    0.40
     অপহরণকারী
    0.40
     beliau
    0.39
     വ്യക്തി
    0.39
     Deacon
    0.39
     halfCanvas
    0.39
     আবরণ
    0.39
     nw
    0.38
    Activations Density 0.001%

    No Known Activations