© 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. 45676
    Prev
    Next
    INDEX
    Explanations

    graphql, caliban, types

    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
     farms
    -0.72
     padx
    -0.69
    poietic
    -0.69
     atteinte
    -0.68
     όμως
    -0.67
    llä
    -0.67
     DMCA
    -0.67
     передний
    -0.67
    Procedure
    -0.67
    يه
    -0.67
    POSITIVE LOGITS
    McC
    0.84
    лася
    0.75
     kā
    0.75
    FECT
    0.75
    EXO
    0.73
     Shelly
    0.73
     McC
    0.72
    lauben
    0.71
     Avant
    0.70
     kommunik
    0.70
    Activations Density 0.025%

    No Known Activations