© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11461
    Prev
    Next
    INDEX
    Explanations

    the following, next, full

    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
     all
    -2.45
     not
    -2.28
     other
    -2.17
     both
    -2.06
     still
    -1.95
     some
    -1.82
     now
    -1.81
     first
    -1.79
     only
    -1.77
     such
    -1.77
    POSITIVE LOGITS
     Dinas
    1.45
     poème
    1.41
     maniere
    1.41
    ."/
    1.38
     ?-
    1.38
    itize
    1.35
     Atención
    1.35
    ilies
    1.34
    ithe
    1.34
    шую
    1.34
    Activations Density 0.050%

    No Known Activations