© 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. 118544
    Prev
    Next
    INDEX
    Explanations

    code prefixes and structures

    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
     filepath
    -0.75
     Badezimmer
    -0.74
     laminated
    -0.72
    ramo
    -0.72
     Oils
    -0.72
     purple
    -0.72
     archers
    -0.71
     卫
    -0.71
     בן
    -0.71
     τί
    -0.71
    POSITIVE LOGITS
    SIP
    0.82
     SIP
    0.81
    🏊
    0.80
    ！"
    0.80
     GoogleFonts
    0.79
     Afric
    0.78
     turbin
    0.77
    "},
    0.77
    !")
    0.77
     fura
    0.76
    Activations Density 0.012%

    No Known Activations