© 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. 108369
    Prev
    Next
    INDEX
    Explanations

    http or https links

    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
     after
    -1.02
     which
    -0.96
     for
    -0.96
     only
    -0.93
     out
    -0.86
     with
    -0.86
     presents
    -0.85
     whose
    -0.85
     relating
    -0.83
     offered
    -0.82
    POSITIVE LOGITS
     assets
    1.33
    assets
    1.30
     ASSETS
    1.29
     images
    1.27
    twimg
    1.25
    img
    1.23
    cdn
    1.22
     img
    1.19
     Wikimedia
    1.05
    jpg
    1.05
    Activations Density 0.004%

    No Known Activations