© 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. 102680
    Prev
    Next
    INDEX
    Explanations

    in binary

    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
    getQuery
    -0.73
    agte
    -0.72
     Wanderers
    -0.71
     accept
    -0.70
    Accept
    -0.68
    PAP
    -0.66
     accepts
    -0.65
     Accept
    -0.64
    nikom
    -0.63
     igenom
    -0.63
    POSITIVE LOGITS
     heck
    0.83
     hell
    0.75
    地狱
    0.67
     HELL
    0.65
     rebuilding
    0.65
     бое
    0.65
    heck
    0.65
    orks
    0.65
     schoon
    0.64
    lichung
    0.63
    Activations Density 0.063%

    No Known Activations