© 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. 23726
    Prev
    Next
    INDEX
    Explanations

    which followed by conjunctions or descriptions

    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
     there
    -1.12
    色々な
    -1.01
    いかがでしたか
    -0.98
    —“
    -0.94
    に従
    -0.92
    phylactic
    -0.91
     né
    -0.90
    led
    -0.88
    他に
    -0.88
     общего
    -0.86
    POSITIVE LOGITS
     ones
    2.41
    Ones
    1.72
     Ones
    1.51
     والتي
    1.40
     stuff
    1.39
     things
    1.21
    ones
    1.16
     coisas
    1.14
    iligt
    1.05
     şeyler
    1.05
    Activations Density 0.097%

    No Known Activations