© 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. 4355
    Prev
    Next
    INDEX
    Explanations

    street lamps

    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
    BUILDING
    -0.85
    dey
    -0.79
     FEN
    -0.77
     Floors
    -0.77
    FLOOR
    -0.77
     puzz
    -0.74
     mezzanine
    -0.74
    floor
    -0.74
     building
    -0.73
     airsoft
    -0.73
    POSITIVE LOGITS
     pole
    1.91
     street
    1.89
     poles
    1.81
     lamp
    1.63
    pole
    1.58
    Street
    1.49
    street
    1.42
    Pole
    1.42
    poles
    1.41
     Pole
    1.41
    Activations Density 0.026%

    No Known Activations