Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8790
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions

    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
     endforeach
    -0.80
    フード
    -0.75
     Hinter
    -0.72
     if
    -0.71
     or
    -0.71
     hilang
    -0.70
    lesen
    -0.69
     hija
    -0.68
    %,
    -0.68
     confetti
    -0.68
    POSITIVE LOGITS
     numerator
    1.58
    mfrac
    1.22
     fraction
    1.07
    numerator
    1.02
     denominator
    1.02
     Fraction
    0.96
    frac
    0.91
    Fraction
    0.90
     fractions
    0.86
    fraction
    0.83
    Activations Density 0.000%

    No Known Activations