© 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. 66161
    Prev
    Next
    INDEX
    Explanations

    HTML heading and title tags

    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
     llegará
    -0.90
     își
    -0.86
    何度も
    -0.84
    toim
    -0.84
     ナイキ
    -0.83
     Belastung
    -0.83
    HtmlAttribute
    -0.81
     marginTop
    -0.81
     octombrie
    -0.80
     aprilie
    -0.80
    POSITIVE LOGITS
    <h4>
    0.88
    <h5>
    0.77
     kombin
    0.75
    h
    0.75
    cytes
    0.73
    baijan
    0.73
     glow
    0.73
    Addon
    0.71
    Sega
    0.71
     bubbling
    0.69
    Activations Density 0.005%

    No Known Activations