© 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. 22-GEMMASCOPE-RES-131K
    4. 418
    Prev
    Next
    INDEX
    Explanations

    person described by their fame

    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_22/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
     when
    -2.20
     with
    -2.20
     at
    -2.09
     it
    -1.97
     each
    -1.96
     for
    -1.95
     three
    -1.90
     while
    -1.86
     after
    -1.86
     will
    -1.84
    POSITIVE LOGITS
     alho
    1.80
     applau
    1.77
     herbes
    1.70
     inond
    1.66
     pittores
    1.66
     charmant
    1.66
    茈
    1.63
     constater
    1.61
    粜
    1.59
     célè
    1.58
    Activations Density 0.019%

    No Known Activations