© 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. 34646
    Prev
    Next
    INDEX
    Explanations

    small or small caps

    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
    чай
    -0.73
     боро
    -0.71
    αρ
    -0.71
    ologio
    -0.66
    scanner
    -0.65
     البلاد
    -0.65
    нтів
    -0.65
    пев
    -0.65
     ض
    -0.64
    engo
    -0.64
    POSITIVE LOGITS
     small
    3.45
    Small
    3.25
     Small
    3.17
    small
    3.13
     SMALL
    2.70
    SMALL
    2.61
     pequeños
    2.05
     pequeño
    1.98
     pequeña
    1.98
    小
    1.95
    Activations Density 0.045%

    No Known Activations