© 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. 10-GEMMASCOPE-RES-131K
    7. 66485
    Prev
    Next
    INDEX
    Explanations

    biotic and abiotic factors

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

    terms related to environmental biology, specifically identifying words like "biotic" and "abiotic" in scientific contexts.

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

    The neuron detects occurrences of the words “biotic” and “abiotic,” i.e. mentions of biotic or abiotic environmental factors.

    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
     ”
    -2.61
    of
    -2.23
     to
    -2.16
     “
    -2.09
     perché
    -2.06
    vible
    -2.02
    tedì
    -1.98
     ’
    -1.96
     или
    -1.93
    っている
    -1.93
    POSITIVE LOGITS
    {
    2.17
    枓
    2.08
    this
    2.05
    .
    2.03
    桄
    2.03
     untuk
    1.99
     bringe
    1.95
     сожа
    1.86
    
    1.84
    宝物
    1.82
    Activations Density 0.007%

    No Known Activations