© 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. 57500
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    跤
    -0.82
     all
    -0.81
     appears
    -0.80
     comparatively
    -0.79
     might
    -0.78
     lilac
    -0.78
    tiglie
    -0.77
    presso
    -0.75
     Earlier
    -0.75
     Had
    -0.74
    POSITIVE LOGITS
    citation
    1.30
     citation
    1.12
    источник
    1.05
     nécess
    1.02
     nécessite
    1.00
    Citation
    1.00
     véri
    0.90
    wurde
    0.89
    cite
    0.88
     источник
    0.88
    Activations Density 0.003%

    No Known Activations