© 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. 100044
    Prev
    Next
    INDEX
    Explanations

    modelmodel or serial numbers

    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
     certain
    -1.81
     anunciou
    -1.68
     encontram
    -1.60
     informou
    -1.58
     Якщо
    -1.57
     categorized
    -1.56
     concernés
    -1.54
     another
    -1.53
    余談
    -1.53
     capacidades
    -1.52
    POSITIVE LOGITS
    ’
    2.27
    ING
    1.63
    ２
    1.59
    ↵
    1.51
    =”
    1.50
    ↵↵↵
    1.48
     klar
    1.47
    “,
    1.47
    >${
    1.46
    6
    1.44
    Activations Density 0.032%

    No Known Activations