© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30153
    Prev
    Next
    INDEX
    Explanations

    WRITE connected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ALC
    -0.88
     carottes
    -0.81
    tizens
    -0.77
     Hooper
    -0.76
    Leary
    -0.76
    contra
    -0.72
    blech
    -0.71
    താ
    -0.70
    letas
    -0.70
     milestones
    -0.69
    POSITIVE LOGITS
     enable
    1.32
     Enable
    1.27
    Enable
    1.25
     control
    1.12
    ENABLE
    1.10
     controls
    1.05
     enabling
    1.05
    enable
    1.01
    CONTROL
    1.00
    控制
    0.97
    Activations Density 0.023%

    No Known Activations