© 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. 106002
    Prev
    Next
    INDEX
    Explanations

    am + idine, am + ides, am + ined, am + ala

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

    The neuron detects words containing "am" syllables, particularly in scientific or technical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     และ
    -2.89
    𖣘
    -2.80
    出来ました
    -2.63
    铪
    -2.61
    峮
    -2.61
     rád
    -2.61
    驁
    -2.61
    ﻒ
    -2.59
    渀
    -2.56
    ;
    -2.55
    POSITIVE LOGITS
    am
    3.88
    s
    3.50
    X
    3.20
    M
    2.78
    la
    2.78
    ol
    2.75
    S
    2.69
    B
    2.63
    re
    2.56
    H
    2.56
    Activations Density 0.029%

    No Known Activations