© 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. 62683
    Prev
    Next
    INDEX
    Explanations

    comments following markers

    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
     even
    -1.26
     their
    -1.21
     (
    -1.13
     if
    -1.07
     in
    -1.05
     easy
    -1.03
     enhanced
    -1.02
     when
    -1.02
     an
    -1.01
     enhance
    -1.01
    POSITIVE LOGITS
     comments
    1.18
     deliciously
    1.10
     comentário
    1.02
     fervent
    1.02
     magnific
    1.00
     wonderfully
    0.99
     meravigli
    0.99
     delightfully
    0.98
    selben
    0.98
     koment
    0.98
    Activations Density 0.000%

    No Known Activations