© 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. 62734
    Prev
    Next
    INDEX
    Explanations

    numbers followed by '+'

    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
     those
    -0.99
     уже
    -0.91
     with
    -0.90
     Hentet
    -0.90
     that
    -0.90
     like
    -0.88
     when
    -0.87
     quite
    -0.84
     Already
    -0.84
    هاز
    -0.82
    POSITIVE LOGITS
     online
    1.05
    ή
    0.93
     presentation
    0.92
    [,
    0.91
     présentation
    0.90
    SAMPLE
    0.86
     apresentação
    0.85
     interac
    0.84
    ningar
    0.84
    lire
    0.83
    Activations Density 0.001%

    No Known Activations