© 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. 34-GEMMASCOPE-RES-131K
    7. 115687
    Prev
    Next
    INDEX
    Explanations

    numbers and word prefixes

    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
    evaluated
    -0.70
    ³
    -0.63
    Nbr
    -0.63
    showed
    -0.62
    squid
    -0.61
     Sustain
    -0.61
    フィル
    -0.61
     Decentral
    -0.61
     दिख
    -0.61
     Breed
    -0.59
    POSITIVE LOGITS
    nim
    0.79
     phones
    0.79
    夜
    0.77
     Peti
    0.77
    Roo
    0.76
    🍯
    0.75
    wagon
    0.75
     espírito
    0.75
    CLE
    0.73
    Dichloroethene
    0.73
    Activations Density 0.025%

    No Known Activations