© 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. 22-GEMMASCOPE-RES-131K
    7. 69150
    Prev
    Next
    INDEX
    Explanations

    people's ages

    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
     diversos
    -1.77
     différents
    -1.76
     lauded
    -1.70
     verschillende
    -1.68
     suscit
    -1.58
     reiter
    -1.54
     possi
    -1.52
     traduc
    -1.49
     magnific
    -1.47
     monstrous
    -1.47
    POSITIVE LOGITS
     through
    2.06
     because
    1.84
     in
    1.80
     after
    1.71
     fashioned
    1.70
     when
    1.70
     with
    1.63
     from
    1.62
     gustaMe
    1.55
     despite
    1.52
    Activations Density 0.019%

    No Known Activations