© 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. 62723
    Prev
    Next
    INDEX
    Explanations

    mathematical vectors

    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
    曲を
    -0.76
    ୍
    -0.73
    zae
    -0.73
    fohlen
    -0.70
     ratio
    -0.67
    Exchange
    -0.67
     exchange
    -0.67
     Men
    -0.66
     annak
    -0.66
    aphne
    -0.65
    POSITIVE LOGITS
     vector
    3.45
     vectors
    2.81
    vector
    2.75
    Vector
    2.70
     Vector
    2.61
    向量
    2.36
     vektor
    2.25
     vec
    2.22
     вектор
    2.19
    VECTOR
    2.14
    Activations Density 0.042%

    No Known Activations