© 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. 23779
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and words

    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
    uawei
    -0.67
    είο
    -0.66
    seems
    -0.65
    weiten
    -0.65
    ləş
    -0.64
    
    -0.63
    limate
    -0.63
    zeigt
    -0.63
    莠
    -0.62
     Sonn
    -0.61
    POSITIVE LOGITS
     kvm
    0.81
    堿
    0.71
    sector
    0.69
     Numa
    0.67
    anten
    0.65
    osan
    0.65
    anadium
    0.65
     silueta
    0.65
    機關
    0.65
    osin
    0.64
    Activations Density 0.060%

    No Known Activations