© 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. 10-GEMMASCOPE-RES-131K
    7. 14765
    Prev
    Next
    INDEX
    Explanations

    Felipe Anderson, Bola, caterpillar

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

    The neuron fires on occurrences of the word “caterpillar” (including its sub-parts like CATER, PILLAR).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -
    -3.98
     .
    -3.59
     "
    -3.30
     I
    -3.30
     (
    -3.08
     l
    -3.02
    ↵↵
    -2.91
     $
    -2.88
     r
    -2.72
    …
    -2.72
    POSITIVE LOGITS
    ſelves
    3.92
    艫
    3.72
    鐒
    3.47
    
    3.34
    孥
    3.34
    ⢪
    3.30
    ⚋
    3.20
     发型
    3.13
    戩
    3.08
    鄚
    3.08
    Activations Density 0.004%

    No Known Activations