© 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. 66136
    Prev
    Next
    INDEX
    Explanations

    user directories and paths

    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
     before
    -1.90
     at
    -1.84
     in
    -1.74
     as
    -1.72
     it
    -1.71
     or
    -1.65
     not
    -1.62
     what
    -1.61
     when
    -1.60
     from
    -1.59
    POSITIVE LOGITS
     gigantic
    1.63
     goofy
    1.54
     insanely
    1.48
     colossal
    1.48
     amazingly
    1.44
     dilapidated
    1.43
     marvelous
    1.41
    튿
    1.41
     exceedingly
    1.40
     magnificent
    1.36
    Activations Density 0.004%

    No Known Activations