© 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. 58671
    Prev
    Next
    INDEX
    Explanations

    gerunds describing 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_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
     القرار
    -0.88
    bular
    -0.81
     divino
    -0.80
     déri
    -0.79
    夹
    -0.77
    ​​​​
    -0.75
    に向
    -0.74
    })=
    -0.74
    っぽい
    -0.74
    numerusform
    -0.73
    POSITIVE LOGITS
     woman
    0.96
     women
    0.95
    ettbewerb
    0.93
     individuals
    0.89
     eyes
    0.86
    lovak
    0.84
    est
    0.81
    0.81
     families
    0.81
     children
    0.80
    Activations Density 0.034%

    No Known Activations