© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98769
    Prev
    Next
    INDEX
    Explanations

    9, 4, 1, 2

    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
    Mahon
    -0.88
    arno
    -0.77
     במח
    -0.75
    ouard
    -0.75
    炀
    -0.74
     chiffon
    -0.73
     למש
    -0.73
    loma
    -0.72
     lemons
    -0.72
     rotors
    -0.72
    POSITIVE LOGITS
     verv
    0.75
    ApiService
    0.73
     духовке
    0.71
    bst
    0.70
     JSONException
    0.70
    forEach
    0.69
     Brüder
    0.69
     Zellen
    0.69
     effector
    0.69
    感じ
    0.68
    Activations Density 0.024%

    No Known Activations