© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101129
    Prev
    Next
    INDEX
    Explanations

    online forums

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs and references to online forums or community websites.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    There
    -1.91
     to
    -1.82
     there
    -1.77
     by
    -1.71
     that
    -1.66
    Some
    -1.63
     at
    -1.63
     on
    -1.62
    If
    -1.42
     There
    -1.41
    POSITIVE LOGITS
     têtes
    1.38
    ⬈
    1.36
     vertus
    1.34
     forum
    1.33
    ícias
    1.33
     étages
    1.32
     nimmer
    1.32
    茈
    1.30
     miejscowości
    1.30
     débat
    1.29
    Activations Density 0.043%

    No Known Activations