© 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. 107951
    Prev
    Next
    INDEX
    Explanations

    legal or regulatory stipulations

    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
     både
    -0.86
    鬓
    -0.83
     samtidigt
    -0.82
     disponível
    -0.81
    晚了
    -0.81
     Sebasti
    -0.81
    aah
    -0.80
     sowohl
    -0.80
    ocity
    -0.79
     faber
    -0.79
    POSITIVE LOGITS
     bona
    1.66
     purely
    1.55
     solely
    1.46
     merely
    1.35
     genuinely
    1.34
     necessary
    1.30
     legitimate
    1.27
     jedynie
    1.25
     legitimately
    1.23
     truly
    1.23
    Activations Density 0.053%

    No Known Activations