© 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. 71072
    Prev
    Next
    INDEX
    Explanations

    holding, embracing, actions

    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
    ње
    -1.59
    it
    -1.58
    '
    -1.56
    夲
    -1.45
     warszawa
    -1.45
     timeType
    -1.45
     HÀ
    -1.45
     there
    -1.42
    佉
    -1.39
     '
    -1.38
    POSITIVE LOGITS
     “
    1.52
    tious
    1.38
     naturales
    1.34
     ابتدا
    1.30
     bolsas
    1.29
    nels
    1.27
     veren
    1.25
     کامل
    1.24
     DOS
    1.23
    ageable
    1.23
    Activations Density 0.010%

    No Known Activations