© 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. 77771
    Prev
    Next
    INDEX
    Explanations

    carbon nanotubes

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

    references to carbon nanotubes (CNTs) and related nanotechnology terms.

    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
     Octave
    -0.74
    culoskeletal
    -0.72
     MVP
    -0.71
    љено
    -0.71
    refundable
    -0.71
     \<
    -0.70
     lactic
    -0.70
     governors
    -0.70
     holog
    -0.69
     HUAWEI
    -0.69
    POSITIVE LOGITS
     carbon
    1.30
     Carbon
    1.28
     tubes
    1.27
    carbon
    1.27
    tube
    1.27
    Carbon
    1.27
     nanotubes
    1.23
     fuller
    1.20
    tubes
    1.19
     SW
    1.13
    Activations Density 0.069%

    No Known Activations