© 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. 75202
    Prev
    Next
    INDEX
    Explanations

    amino, omino, umino, imino suffixes

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

    chemical compound names with the suffix "-amin" or related chemical terms in scientific contexts.

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

    The neuron strongly responds to any token containing the letter sequence “min” (as found in chemical names like “piperlongumine,” “aminoglycans,” 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
    al
    -2.77
    齶
    -2.63
    izione
    -2.61
    derdag
    -2.58
    躥
    -2.53
    alakip
    -2.44
     manifestación
    -2.42
     surpass
    -2.41
    ſelf
    -2.38
     Segurança
    -2.36
    POSITIVE LOGITS
    釓
    3.14
    来ました
    2.31
    Ꮨ
    2.22
    芣
    2.22
    ,
    2.16
    			
    2.14
     inconvénients
    2.13
    的大
    2.09
     allah
    2.02
    :
    2.02
    Activations Density 0.024%

    No Known Activations