© 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. 10-GEMMASCOPE-RES-131K
    7. 80755
    Prev
    Next
    INDEX
    Explanations

    species of

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

    phrases that describe the number of species in a biological genus.

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

    The neuron flags numeric expressions quantifying species (e.g. counts of species in a genus or similar taxonomic statistics).

    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
     a
    -1.79
     "
    -1.67
    ᾿
    -1.41
     option
    -1.38
    ("
    -1.29
    bly
    -1.29
    termilk
    -1.28
    ,--
    -1.27
     for
    -1.26
     an
    -1.26
    POSITIVE LOGITS
     of
    1.55
    garder
    1.37
     cucchiai
    1.37
     squadre
    1.33
    gén
    1.33
    fficking
    1.33
    kundige
    1.33
    也會
    1.31
     spagnolo
    1.27
    momile
    1.26
    Activations Density 0.246%

    No Known Activations