© 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. 101022
    Prev
    Next
    INDEX
    Explanations

    i thought i'd do

    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
     seleccionadas
    -1.96
     funcionales
    -1.77
     esenciales
    -1.77
     variadas
    -1.71
    ti
    -1.70
     each
    -1.67
     adecuadas
    -1.66
     sufficient
    -1.66
     habituales
    -1.66
     Instead
    -1.64
    POSITIVE LOGITS
    andte
    1.41
    🛇
    1.39
    СТИ
    1.36
    弱点
    1.36
    ören
    1.36
    они
    1.36
    weilen
    1.35
    ть
    1.35
    一闪
    1.35
    zeniem
    1.33
    Activations Density 0.010%

    No Known Activations