© 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. 118409
    Prev
    Next
    INDEX
    Explanations

    wall or walls

    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
    kela
    -0.84
    oire
    -0.81
    vierno
    -0.77
    lineTo
    -0.76
    berglass
    -0.75
     וּ
    -0.74
    воде
    -0.74
    讞
    -0.73
    leggio
    -0.73
    ctice
    -0.73
    POSITIVE LOGITS
     walls
    5.38
     wall
    5.19
    walls
    3.66
    wall
    3.64
     Walls
    3.53
    Walls
    3.34
     WALL
    3.25
     Wall
    3.25
    Wall
    3.23
    壁
    3.17
    Activations Density 0.120%

    No Known Activations