© 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. 65869
    Prev
    Next
    INDEX
    Explanations

    access defined

    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
     nativo
    -0.84
    疣
    -0.81
     kriti
    -0.78
    血管
    -0.77
    вня
    -0.75
    。”
    -0.75
     Banken
    -0.75
     Якщо
    -0.74
     temporaire
    -0.74
    homogeneous
    -0.73
    POSITIVE LOGITS
     access
    1.03
     included
    1.02
     defined
    1.00
    define
    0.96
     exit
    0.93
     absolute
    0.92
     wp
    0.86
     define
    0.85
     direct
    0.83
     entry
    0.82
    Activations Density 0.041%

    No Known Activations