© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130021
    Prev
    Next
    INDEX
    Explanations

    The neuron flags personal, first-person opinion and review language (e.g. “I,” “my,” “we,” and other self-referential statements giving a personal take).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    restaurants and establishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ristorante
    -1.61
    iamo
    -1.33
     dialami
    -1.25
     cabaña
    -1.24
    étés
    -1.24
     Mexiko
    -1.21
     помощью
    -1.20
    犷
    -1.20
    toast
    -1.17
    ële
    -1.17
    POSITIVE LOGITS
     establishment
    1.52
    Employees
    1.30
     locale
    1.23
    ﻻ
    1.20
    Located
    1.20
     locals
    1.18
    новая
    1.17
     visiting
    1.16
     семь
    1.16
    ınca
    1.14
    Activations Density 0.028%

    No Known Activations