© 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. 106707
    Prev
    Next
    INDEX
    Explanations

    Gross anatomy, computer code, Zinc deficiency

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

    copyright or license header blocks in source code files.

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

    The neuron detects large comment‐block decorations (long runs of asterisks or similar block‐comment delimiter patterns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    눗
    -0.82
    zeum
    -0.82
    genza
    -0.82
    Splitter
    -0.81
    "]="
    -0.79
    ردد
    -0.79
    organization
    -0.79
     kyl
    -0.78
    álva
    -0.75
     demostrado
    -0.75
    POSITIVE LOGITS
    حدث
    0.83
    འ
    0.77
    洼
    0.75
     eti
    0.75
     such
    0.74
    ក
    0.72
     titration
    0.72
     JIT
    0.72
    AAA
    0.71
     Kola
    0.71
    Activations Density 0.060%

    No Known Activations