© 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. 82405
    Prev
    Next
    INDEX
    Explanations

    numerical rounding and approximations

    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
     sanno
    -0.87
    Morte
    -0.84
     تجه
    -0.75
     jät
    -0.73
     часа
    -0.71
    价格
    -0.70
     Uribe
    -0.70
     interests
    -0.70
    Rua
    -0.69
     endTime
    -0.69
    POSITIVE LOGITS
     tenths
    2.17
     tenth
    1.91
    tenths
    1.83
    tenth
    1.58
     fractions
    1.47
     half
    1.41
     fraction
    1.37
     fractional
    1.21
     (.
    1.18
     decimal
    1.09
    Activations Density 0.027%

    No Known Activations