© 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. 73486
    Prev
    Next
    INDEX
    Explanations

    Runtime, Samuel, base,RUN, :

    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
    ţe
    -0.83
    tahanan
    -0.80
     хотели
    -0.79
     objekt
    -0.77
     สม
    -0.75
     PyTuple
    -0.74
    según
    -0.73
    örm
    -0.73
    〘
    -0.73
    ⌇
    -0.73
    POSITIVE LOGITS
    yaret
    0.84
     gestalten
    0.82
     листо
    0.81
     gerekli
    0.80
    watering
    0.78
     participate
    0.77
     ovi
    0.77
    lerinin
    0.75
     sheen
    0.74
    izaci
    0.74
    Activations Density 0.001%

    No Known Activations