© 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. 98764
    Prev
    Next
    INDEX
    Explanations

    flesh and bone, flesh-hungry, fleshy tissue

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

    The neuron detects the word "flesh" and related terms describing physical body parts or substance.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    דור
    -0.79
     embarazada
    -0.76
     télécharger
    -0.75
     gelombang
    -0.75
     gioco
    -0.75
    的模样
    -0.75
     biztons
    -0.74
    seys
    -0.73
     descrição
    -0.73
     aliran
    -0.73
    POSITIVE LOGITS
     flesh
    3.23
    flesh
    2.56
     Flesh
    2.38
    Flesh
    2.06
     fles
    1.86
    肉
    1.59
    fles
    1.52
     fleshy
    1.45
     meat
    1.41
     肉
    1.32
    Activations Density 0.008%

    No Known Activations