© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84733
    Prev
    Next
    INDEX
    Explanations

    indeed

    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
     bè
    -1.62
    opies
    -1.55
    lllllll
    -1.52
    ৢ
    -1.52
     знали
    -1.51
    bedded
    -1.48
     OTHER
    -1.47
    
    -1.47
     definitiv
    -1.46
    龗
    -1.45
    POSITIVE LOGITS
    They
    1.92
    (
    1.77
     would
    1.61
     will
    1.53
     seems
    1.51
    他们
    1.45
    they
    1.41
     tarvit
    1.35
    不少
    1.34
     seemed
    1.32
    Activations Density 0.013%

    No Known Activations