© 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. 10-GEMMASCOPE-RES-131K
    7. 12270
    Prev
    Next
    INDEX
    Explanations

    version identifiers (alpha, beta)

    np_acts-logits-general · gemini-2.5-flash-lite

    version identifiers containing "alpha" or "beta" in software code and configuration files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     are
    -2.25
    ?
    -1.96
     to
    -1.90
     knows
    -1.85
     when
    -1.77
    ys
    -1.69
     during
    -1.67
     then
    -1.66
     don
    -1.62
     In
    -1.54
    POSITIVE LOGITS
     diki
    2.03
     parfü
    1.86
     abiye
    1.70
     tunik
    1.65
     normalt
    1.63
     отзывы
    1.60
     helst
    1.59
     его
    1.59
    Mereka
    1.58
     menyen
    1.58
    Activations Density 0.003%

    No Known Activations