© 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. 22147
    Prev
    Next
    INDEX
    Explanations

    graphite and related materials

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

    The neuron detects the word "graphite" and related carbon materials in scientific/technical contexts.

    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_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
    ING
    -3.39
    甃
    -2.81
    ti
    -2.53
    ⡑
    -2.52
    ῞
    -2.52
     was
    -2.50
    la
    -2.50
    ni
    -2.48
    ates
    -2.45
     dieß
    -2.42
    POSITIVE LOGITS
     When
    3.05
    瞑
    2.73
    驀
    2.63
    しなければ
    2.44
    ！】
    2.42
    五日
    2.39
     suficientemente
    2.33
    あります
    2.31
     Когда
    2.30
    ではまた
    2.30
    Activations Density 0.002%

    No Known Activations