© 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. 87167
    Prev
    Next
    INDEX
    Explanations

    counting items or occurrences

    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
    兩
    -0.98
    ȶ
    -0.91
     Internation
    -0.91
    Why
    -0.87
     Considered
    -0.84
     Ultimately
    -0.83
     oscura
    -0.83
     quantità
    -0.83
     Seem
    -0.83
     Primarily
    -0.82
    POSITIVE LOGITS
    ering
    1.73
    erex
    1.62
    rys
    1.54
    downs
    1.48
    (*)
    1.27
    inu
    1.25
    ered
    1.23
    inho
    1.23
     COUN
    1.21
    erd
    1.20
    Activations Density 0.021%

    No Known Activations