© 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. 62729
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure endings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    獎
    -0.75
    clk
    -0.75
     abiti
    -0.72
     teritor
    -0.71
     Affirmative
    -0.70
    uhn
    -0.67
    yeh
    -0.64
    assertRaises
    -0.63
     Awards
    -0.62
    zug
    -0.62
    POSITIVE LOGITS
     passando
    0.69
     borrowers
    0.68
     calculus
    0.67
    Contributor
    0.65
    omé
    0.65
     Tobi
    0.64
     abgesch
    0.63
    vau
    0.63
     delaying
    0.63
    审核
    0.63
    Activations Density 0.048%

    No Known Activations