© 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. 3652
    Prev
    Next
    INDEX
    Explanations

    proposed proposals investigations

    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
    update
    -0.87
    Local
    -0.87
     inspira
    -0.85
    ####
    -0.85
    изнь
    -0.83
     fama
    -0.82
    LOCAL
    -0.81
     columnIndex
    -0.79
    갱
    -0.79
     shortages
    -0.77
    POSITIVE LOGITS
     format
    1.26
     breakaway
    1.19
     proposal
    1.13
     формат
    1.11
     proposed
    1.07
    proposal
    0.99
    proposed
    0.99
     proposals
    0.99
    proposals
    0.97
    PROPOSED
    0.96
    Activations Density 0.024%

    No Known Activations