© 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. 117814
    Prev
    Next
    INDEX
    Explanations

    statistically significant findings

    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
    apia
    -0.84
    тилась
    -0.82
     Nev
    -0.81
    yonel
    -0.81
    ческом
    -0.80
    ontal
    -0.79
    ücken
    -0.78
    ciamento
    -0.74
    Paladin
    -0.74
    滙
    -0.74
    POSITIVE LOGITS
     significantly
    4.28
    significantly
    3.44
     significant
    3.23
     Significantly
    3.05
    Significant
    3.03
    significant
    2.84
     Significant
    2.84
     statistically
    2.72
     SIGNIFIC
    2.25
     signific
    2.20
    Activations Density 0.350%

    No Known Activations