© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2797
    Prev
    Next
    INDEX
    Explanations

    bricks and thick walls

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on occurrences of the word “wall” (and related plural “walls”), especially in “wall of” constructions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     英雄
    -0.81
    ModelAdmin
    -0.80
    umesc
    -0.80
    Sede
    -0.79
     disarmament
    -0.78
    ļas
    -0.78
     hillside
    -0.78
    Awake
    -0.77
     decking
    -0.77
    PROTO
    -0.75
    POSITIVE LOGITS
     brick
    1.31
     bricks
    1.30
     thickness
    1.10
    bricks
    1.02
    brick
    1.01
     Brick
    1.00
     thicker
    0.99
     erected
    0.94
     partition
    0.91
     solid
    0.90
    Activations Density 0.025%

    No Known Activations