© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55786
    Prev
    Next
    INDEX
    Explanations

    legal case citations

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

    The neuron selectively activates on numeric tokens (pure digits or digit‐containing codes), i.e. it finds numbers and numeric sequences 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_34/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
     costi
    -1.12
     tunn
    -1.08
     procra
    -1.08
     »>
    -0.99
    }}/>
    -0.98
     bianca
    -0.98
    🤍
    -0.97
     assin
    -0.97
    ✨✨
    -0.96
    🥲
    -0.96
    POSITIVE LOGITS
     see
    1.09
     
    0.93
    كيف
    0.92
    see
    0.90
    giá
    0.87
     fört
    0.87
    acion
    0.86
    terraform
    0.85
    อยาก
    0.85
    OnInit
    0.85
    Activations Density 0.000%

    No Known Activations