© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 219949
    Prev
    Next
    INDEX
    Explanations

    describing states and actions

    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
    Negative Logits
     Nu
    0.50
    Nu
    0.49
    github
    0.48
    苏
    0.46
    z
    0.44
    sv
    0.43
    su
    0.43
     关于
    0.42
    yaa
    0.42
     Nou
    0.41
    POSITIVE LOGITS
     conceive
    0.43
     caudal
    0.42
     secretions
    0.42
     degassing
    0.42
     excreted
    0.42
     intravenously
    0.41
     trotz
    0.40
     erythro
    0.39
     circumstance
    0.39
     ventricular
    0.39
    Activations Density 0.000%

    No Known Activations