© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50257
    Prev
    Next
    INDEX
    Explanations

    in range loops

    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
     Româ
    -0.96
     artesanía
    -0.88
    empatan
    -0.82
     ANIMALS
    -0.81
     TECHNI
    -0.80
     entregó
    -0.79
     Säure
    -0.79
    错误
    -0.79
    viš
    -0.77
     Occ
    -0.75
    POSITIVE LOGITS
     range
    2.33
    range
    1.44
     ranging
    1.23
     ranged
    1.09
     ranges
    1.08
    RANGE
    1.01
    Range
    0.98
    ranging
    0.98
     Range
    0.96
    OutOfRange
    0.84
    Activations Density 0.002%

    No Known Activations