© 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. 76465
    Prev
    Next
    INDEX
    Explanations

    highways and major routes

    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
    docks
    -0.77
    groupBox
    -0.77
     ارزش
    -0.76
     braços
    -0.76
    ńskiego
    -0.74
     sessions
    -0.73
     weißen
    -0.72
    ས
    -0.71
     pequenos
    -0.71
     شناسی
    -0.71
    POSITIVE LOGITS
     highway
    3.36
     highways
    2.98
     motorway
    2.77
     freeway
    2.66
     Highway
    2.42
    highway
    2.34
     interstate
    2.19
     Highways
    2.16
    Highway
    2.11
    高速
    2.06
    Activations Density 0.048%

    No Known Activations