© 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. 106641
    Prev
    Next
    INDEX
    Explanations

    reserved rights

    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
     here
    -1.92
    here
    -1.16
     اینجا
    -1.01
    这里
    -0.99
     здесь
    -0.97
    ここ
    -0.95
     aquí
    -0.93
     هنا
    -0.91
     disini
    -0.91
    HERE
    -0.90
    POSITIVE LOGITS
     udział
    0.92
     company
    0.90
     achieve
    0.84
     Often
    0.83
    Some
    0.82
     Some
    0.81
     around
    0.80
     innovative
    0.79
     reż
    0.76
    บ
    0.73
    Activations Density 0.024%

    No Known Activations