© 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. 144229
    Prev
    Next
    INDEX
    Explanations

    company social responsibility projects

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

    SessionToken

    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
     রাজনীতিবিদ
    0.45
     Advertising
    0.44
    敕
    0.44
    苏联
    0.43
     Dak
    0.43
     Publisher
    0.42
     Newspapers
    0.42
    蓝
    0.42
    狄
    0.42
    apes
    0.41
    POSITIVE LOGITS
     recru
    0.49
     opro
    0.49
     endometri
    0.48
     fortification
    0.48
     randomized
    0.47
     procedente
    0.47
     upregulation
    0.47
     pneumatic
    0.46
     subpopulations
    0.46
     pluripotent
    0.46
    Activations Density 0.001%

    No Known Activations