© 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. 34-GEMMASCOPE-RES-131K
    7. 1503
    Prev
    Next
    INDEX
    Explanations

    acting

    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_34/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
     mengganggu
    -0.88
     mieste
    -0.87
     läsa
    -0.86
    getService
    -0.84
     kontroli
    -0.82
    тинки
    -0.81
    ánk
    -0.79
    よい
    -0.77
    rungen
    -0.77
    /\
    -0.77
    POSITIVE LOGITS
     act
    4.22
     acted
    4.03
     acting
    3.97
     acts
    3.53
    acting
    3.20
    Act
    3.11
    act
    3.11
     Act
    3.09
    Acting
    3.02
     Acts
    2.84
    Activations Density 0.040%

    No Known Activations