© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99237
    Prev
    Next
    INDEX
    Explanations

    mineralization and chemical transformation

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

    chemical or mineral compounds and elements in scientific or technical contexts.

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

    The neuron selectively activates on technical mineralogical or geochemical terms (e.g., specific minerals, elemental names, and sediment components).

    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
    volezza
    -0.96
    ereço
    -0.89
     strcmp
    -0.85
    stava
    -0.85
    rtype
    -0.85
    łoń
    -0.85
     Straße
    -0.84
    Jegyzetek
    -0.83
    ckett
    -0.82
    ("../
    -0.81
    POSITIVE LOGITS
     secondary
    0.93
     phases
    0.83
     comprador
    0.82
    ེ་
    0.81
     replaced
    0.81
     secund
    0.81
     healed
    0.79
    Fase
    0.79
    replacing
    0.76
    صبحت
    0.76
    Activations Density 0.005%

    No Known Activations