© 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. 10-GEMMASCOPE-RES-131K
    7. 45403
    Prev
    Next
    INDEX
    Explanations

    investigate and learn

    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_10/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
     new
    -1.67
     they
    -1.52
     this
    -1.44
     neue
    -1.36
     allow
    -1.33
     keeping
    -1.27
     there
    -1.26
     kept
    -1.25
     keep
    -1.23
     helping
    -1.19
    POSITIVE LOGITS
     Depuis
    1.36
     dichter
    1.31
     verborgen
    1.23
     interessant
    1.22
    ⇹
    1.21
    蚡
    1.21
    SAME
    1.20
     geladeira
    1.18
     imediatamente
    1.17
     estadounid
    1.16
    Activations Density 0.154%

    No Known Activations