© 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. 10-GEMMASCOPE-RES-131K
    7. 15239
    Prev
    Next
    INDEX
    Explanations

    moist air and environments

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

    The neuron detects the word "moist" in environmental or habitat descriptions.

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

    The neuron fires on occurrences of the word “moist,” i.e. terms explicitly describing humidity or dampness.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     
    -3.09
    甴
    -2.31
     It
    -2.31
     longterm
    -2.25
     Некоторые
    -2.19
    也得
    -2.17
    にお
    -2.13
    璈
    -2.11
    去做
    -2.11
    としても
    -2.11
    POSITIVE LOGITS
    鬭
    2.67
    ꜄
    2.61
    你现在
    2.61
    鷙
    2.53
     και
    2.53
     苹果
    2.41
    壟
    2.38
    軼
    2.36
    和風
    2.30
     и
    2.28
    Activations Density 0.002%

    No Known Activations