© 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. 27658
    Prev
    Next
    INDEX
    Explanations

    HTML template languages

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

    The neuron fires on numeric literals (integer or decimal digit tokens) in the text.

    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
     zwar
    -0.98
     all
    -0.93
     by
    -0.90
     everybody
    -0.89
     усі
    -0.86
     ウィ
    -0.85
     everyone
    -0.85
     from
    -0.83
    )}$.
    -0.83
    }$.
    -0.82
    POSITIVE LOGITS
     cambiare
    1.04
     여성
    0.96
     mantenere
    0.94
    女性の
    0.92
    山形
    0.91
    Bảo
    0.91
     ман
    0.89
    zaj
    0.88
    igte
    0.88
     exé
    0.88
    Activations Density 0.002%

    No Known Activations