© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92274
    Prev
    Next
    INDEX
    Explanations

    dates and community events

    np_acts-logits-general · gemini-2.5-flash-lite

    adjective-noun pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    țile
    0.53
     तुर
    0.51
     Евге
    0.50
    ですので
    0.47
     portland
    0.47
    க்கொள்ள
    0.46
     chieft
    0.46
     ވަ
    0.46
    લ
    0.46
    تان
    0.45
    POSITIVE LOGITS
     perception
    0.44
     DEVELOPMENT
    0.43
     COMMUNITY
    0.42
     Coates
    0.42
     HOST
    0.42
     WILSON
    0.41
     PROFESSIONAL
    0.41
    াজী
    0.40
    Generated
    0.40
     সামনে
    0.40
    Activations Density 0.000%

    No Known Activations