© 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. 48516
    Prev
    Next
    INDEX
    Explanations

    Titanium mineralization

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

    scientific and programming document structures like section headings, parameter settings, and file formatting.

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

    The neuron fires strongly on document structure markers—especially section headings, titles, and other metadata field tokens.

    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
     grass
    -0.84
     during
    -0.79
    bacillus
    -0.78
     selecting
    -0.75
     чесно
    -0.75
    ARKS
    -0.70
    層
    -0.70
    蔭
    -0.70
    hid
    -0.69
     Chaco
    -0.69
    POSITIVE LOGITS
    Pdf
    0.92
    modelBuilder
    0.91
     morph
    0.91
    pdf
    0.84
     zama
    0.83
    nto
    0.83
     Roo
    0.82
    morph
    0.81
    Roo
    0.79
    とろ
    0.77
    Activations Density 0.009%

    No Known Activations