© 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. 75647
    Prev
    Next
    INDEX
    Explanations

    binary representation

    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
    statistik
    -0.81
    地震
    -0.79
     хотела
    -0.75
    午餐
    -0.75
     json
    -0.74
     billed
    -0.73
    RTE
    -0.72
    valla
    -0.72
     dakika
    -0.72
    kipun
    -0.72
    POSITIVE LOGITS
     binary
    2.16
    binary
    1.83
     bit
    1.82
     bits
    1.79
     Binary
    1.71
    Binary
    1.67
    bits
    1.65
    bitset
    1.63
    bit
    1.59
     Bits
    1.47
    Activations Density 0.051%

    No Known Activations