© 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. 128621
    Prev
    Next
    INDEX
    Explanations

    axle and nucleotide

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

    mechanical parts, specifically axles and related automobile components.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on any word containing the substring “axle.”

    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
    h
    -3.72
    \
    -3.41
    "
    -3.36
    y
    -3.30
    ’
    -3.00
    is
    -2.92
    f
    -2.89
    o
    -2.81
    —
    -2.78
    at
    -2.73
    POSITIVE LOGITS
    
    2.78
    驁
    2.78
     optimizar
    2.59
     různých
    2.47
    齜
    2.45
    躄
    2.45
    塤
    2.44
    쩡
    2.42
    哢
    2.42
    砗
    2.42
    Activations Density 0.004%

    No Known Activations