© 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. 47151
    Prev
    Next
    INDEX
    Explanations

    question and answer 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
    Negative Logits
    xspace
    -0.84
    特别是
    -0.79
     secre
    -0.79
    Coucou
    -0.79
     oyunu
    -0.79
    ölcs
    -0.77
     Puppies
    -0.76
    HN
    -0.74
     projectiles
    -0.74
    +".
    -0.74
    POSITIVE LOGITS
    に行ってきました
    0.81
    SqlDataReader
    0.79
    cuses
    0.77
    AndUpdate
    0.74
    rô
    0.72
     adhere
    0.71
    stract
    0.70
     คร
    0.70
     responsável
    0.70
    chure
    0.69
    Activations Density 0.000%

    No Known Activations