© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116732
    Prev
    Next
    INDEX
    Explanations

    soil types and properties

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

    technical descriptions of soil and geological materials in scientific texts.

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

    This neuron activates on terms naming geological or soil materials (and their physical properties), such as rock or soil types (e.g. shale, sand, clay, igneous) and related descriptors (e.g. low conductivity, m/s).

    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
    য়া
    -0.84
    /"+
    -0.79
     điệu
    -0.76
    ToServer
    -0.75
    imshow
    -0.75
     関連
    -0.75
    })-
    -0.75
    miot
    -0.74
    /'+
    -0.74
    ][/
    -0.74
    POSITIVE LOGITS
     clay
    2.11
     sand
    2.05
     sandy
    1.74
     Clay
    1.66
     silt
    1.61
     Sand
    1.55
    Clay
    1.54
    clay
    1.52
     loam
    1.48
    沙
    1.47
    Activations Density 0.023%

    No Known Activations