© 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. 10-GEMMASCOPE-RES-131K
    7. 42973
    Prev
    Next
    INDEX
    Explanations

    spurious outcomes and false information

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

    The neuron is highly selective for the adjective “spurious,” especially in technical or formal contexts.

    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
     Для
    -2.80
     Мы
    -2.41
     Could
    -2.34
     Можно
    -2.33
     SHOULD
    -2.25
    </sup>
    -2.19
     scow
    -2.19
     Owing
    -2.17
     Теперь
    -2.16
    或
    -2.16
    POSITIVE LOGITS
    }
    2.44
    ↵↵
    2.14
    逦
    2.06
    锷
    2.00
    '
    1.98
    鼋
    1.98
     are
    1.93
    衚
    1.91
    🎹
    1.88
     ouvir
    1.88
    Activations Density 0.001%

    No Known Activations