© 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. 66046
    Prev
    Next
    INDEX
    Explanations

    cannabis and frog species names

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

    proper names of people, species, or compounds, particularly those with Latin or scientific origins.

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

    The neuron fires on capitalized or otherwise distinctive named entities—proper names of people, places, publishers, species, etc.

    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
    して下さい
    -2.48
    緜
    -2.44
    ཋ
    -2.39
    哢
    -2.36
    呦
    -2.31
    梘
    -2.22
    捽
    -2.19
    呖
    -2.16
     '
    -2.09
    独特
    -2.08
    POSITIVE LOGITS
    </td>
    2.55
    ’
    2.55
      
    2.41
    d
    2.39
     he
    2.33
    ↵
    2.33
    p
    2.33
    e
    2.31
     "
    2.25
    ra
    2.23
    Activations Density 0.002%

    No Known Activations