© 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. 22-GEMMASCOPE-RES-131K
    7. 75121
    Prev
    Next
    INDEX
    Explanations

    authentic product or quality

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

    The main thing this neuron does is detect words related to brand authenticity and originality (e.g., “branded,” “original,” “authentic,” “genuine,” “authenticity”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ícias
    -1.02
     Ereign
    -1.01
     квіт
    -0.88
    엎
    -0.87
    眺
    -0.86
    🗺
    -0.85
     affitto
    -0.83
    lettes
    -0.82
    anians
    -0.82
     is
    -0.82
    POSITIVE LOGITS
     authentic
    2.17
     authenticity
    2.08
    authentic
    1.98
     genuine
    1.98
     authenticate
    1.67
    Authentic
    1.64
     genu
    1.59
     Authenticity
    1.48
    genuine
    1.47
     autenti
    1.46
    Activations Density 0.045%

    No Known Activations