© 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. 31-GEMMASCOPE-2-RES-65K
    7. 44965
    Prev
    Next
    INDEX
    Explanations

    disposition

    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_65k_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
    кансер
    0.54
     pavatt
    0.50
    вае
    0.50
     эмне
    0.50
    Carter
    0.49
     toneladas
    0.48
    鵬
    0.47
    TestSource
    0.46
    IsPass
    0.46
    вате
    0.46
    POSITIVE LOGITS
     Google
    0.57
     "
    0.52
    0.50
     Z
    0.49
     to
    0.49
     “
    0.48
     POWER
    0.48
     Power
    0.47
     X
    0.46
     P
    0.46
    Activations Density 0.002%

    No Known Activations