© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    crowdfunding projects

    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
     Crow
    -0.94
     crow
    -0.93
    Crow
    -0.85
     Crowd
    -0.84
    degna
    -0.79
     donation
    -0.79
    ường
    -0.79
    crow
    -0.79
    breit
    -0.77
     crowd
    -0.75
    POSITIVE LOGITS
     creators
    0.85
    プロジェクト
    0.80
    tetés
    0.78
    creator
    0.78
     projects
    0.77
     strug
    0.77
     blurb
    0.76
    μαι
    0.74
     project
    0.73
     Acer
    0.73
    Activations Density 0.017%

    No Known Activations