© 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. 34-GEMMASCOPE-RES-131K
    7. 64193
    Prev
    Next
    INDEX
    Explanations

    each time

    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
    []=$
    -0.95
    ByName
    -0.88
    ijoje
    -0.85
    ряду
    -0.85
     mAdapter
    -0.85
    IKO
    -0.84
    Daily
    -0.84
     herhangi
    -0.84
    тьи
    -0.82
    ffilm
    -0.82
    POSITIVE LOGITS
     every
    5.84
     each
    5.78
    每次
    4.69
     everytime
    4.56
     каждый
    4.47
     jedes
    4.28
     setiap
    4.22
    every
    4.16
     chaque
    4.13
     varje
    4.06
    Activations Density 0.205%

    No Known Activations