© 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. 98972
    Prev
    Next
    INDEX
    Explanations

    technical or code constructs

    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
    萬
    -0.81
     萬
    -0.80
    Without
    -0.79
    ﾀ
    -0.79
    韦
    -0.79
     endforeach
    -0.79
     万
    -0.78
    spyOn
    -0.76
    願
    -0.76
     scarcely
    -0.75
    POSITIVE LOGITS
    optimized
    0.94
    point
    0.94
     crescita
    0.90
    arned
    0.90
    création
    0.90
    examined
    0.88
     erhi
    0.88
    activités
    0.88
    atization
    0.87
    -;
    0.86
    Activations Density 0.000%

    No Known Activations