© 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. 70120
    Prev
    Next
    INDEX
    Explanations

    rates per 100,000

    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
    一千
    -1.01
     billions
    -0.98
    三千
    -0.98
    Billi
    -0.80
     млрд
    -0.78
     Billi
    -0.77
    FFFFFFFF
    -0.75
     Billion
    -0.73
     osserva
    -0.72
    ReadByte
    -0.72
    POSITIVE LOGITS
     lakh
    1.24
     lakhs
    1.08
    XXXXXX
    1.06
    百万
    1.00
     quarter
    0.88
    󠁥
    0.84
     Kto
    0.82
    xxxxxx
    0.82
     Lakh
    0.81
     lacs
    0.80
    Activations Density 0.158%

    No Known Activations