© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12709
    Prev
    Next
    INDEX
    Explanations

    campsite or genotype

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

    words ending in "site" or "sis" and genetics-related terminology.

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

    The neuron fires on noun‐forming suffixes (–sis, –site, –type), i.e. on tokens that end with these common noun endings.

    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
    )”
    -3.00
    ⬈
    -2.91
    ”:
    -2.84
    蚴
    -2.73
    ଝ
    -2.64
    槼
    -2.61
     baumwolle
    -2.59
    雠
    -2.59
     itp
    -2.59
    =”
    -2.59
    POSITIVE LOGITS
    ために
    2.61
     если
    2.47
    釭
    2.44
     Если
    2.41
     s
    2.39
    Initially
    2.33
    Normally
    2.33
    )
    2.28
    Certainly
    2.27
    珦
    2.25
    Activations Density 0.003%

    No Known Activations