© 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. 76755
    Prev
    Next
    INDEX
    Explanations

    copyright and license text

    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
     Zelle
    -0.91
    ieur
    -0.83
     gills
    -0.82
    áže
    -0.81
     Musique
    -0.80
    きましたが
    -0.79
    PhysRevLett
    -0.79
    琬
    -0.79
    ంట
    -0.77
    ungkinkan
    -0.76
    POSITIVE LOGITS
     dejes
    0.78
    するように
    0.73
    jectile
    0.73
    痠
    0.71
     runs
    0.71
     entre
    0.69
    yste
    0.69
    ➾
    0.68
    erdin
    0.68
     тү
    0.68
    Activations Density 0.001%

    No Known Activations