© 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. 86312
    Prev
    Next
    INDEX
    Explanations

    comparisons using than

    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
    ↵↵
    -2.34
    0
    -2.28
    .
    -2.27
    1
    -2.22
     We
    -2.13
    ти
    -2.08
     This
    -2.08
     gebeten
    -2.02
     {
    -1.99
    *
    -1.95
    POSITIVE LOGITS
    ༴
    2.34
    趵
    2.22
    書いた
    2.22
     笑顔
    2.17
    却被
    2.06
    indrome
    1.99
     their
    1.95
    liehen
    1.93
    imiento
    1.89
    gulan
    1.87
    Activations Density 0.021%

    No Known Activations