© 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. 60880
    Prev
    Next
    INDEX
    Explanations

    JSON-like structures

    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
     more
    -0.96
     makes
    -0.93
     comes
    -0.93
     will
    -0.87
     with
    -0.87
     becomes
    -0.86
     very
    -0.86
     people
    -0.85
     almost
    -0.85
     out
    -0.84
    POSITIVE LOGITS
    perhaps
    1.04
    primarily
    0.99
     predominantly
    0.99
    possibly
    0.98
    apparently
    0.93
    presumably
    0.93
    IANA
    0.92
    都没
    0.90
    Según
    0.90
     Badan
    0.90
    Activations Density 0.111%

    No Known Activations