© 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. 116924
    Prev
    Next
    INDEX
    Explanations

    fractions and numbers

    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
    moderne
    -0.91
    Cô
    -0.88
     caméra
    -0.86
     moelle
    -0.84
    Equipe
    -0.81
    klassi
    -0.80
    denk
    -0.79
    ֩
    -0.79
    tä
    -0.79
    １
    -0.78
    POSITIVE LOGITS
    さらに
    1.44
     further
    1.27
    更に
    1.25
     doubly
    1.22
     double
    1.16
     ännu
    1.16
    double
    1.12
     nochmals
    1.12
     Further
    1.11
     jeszcze
    1.09
    Activations Density 0.038%

    No Known Activations