© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55616
    Prev
    Next
    INDEX
    Explanations

    bilateral findings

    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
     or
    -2.16
     either
    -2.02
     или
    -1.70
    either
    -1.67
     Either
    -1.63
    Either
    -1.62
    或
    -1.53
     suele
    -1.52
    Often
    -1.48
     often
    -1.43
    POSITIVE LOGITS
     was
    1.43
    optarg
    1.20
     bilateral
    1.17
    ⫻
    1.13
     she
    1.12
    bil
    1.08
     his
    1.08
     her
    1.06
    Desired
    1.04
     left
    1.02
    Activations Density 0.532%

    No Known Activations