© 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. 34-GEMMASCOPE-RES-131K
    7. 48318
    Prev
    Next
    INDEX
    Explanations

    Numbers, abbreviations, or descriptive words

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

    The neuron activates on standalone numeric tokens (digits and multi-digit numbers) 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
     it
    -1.32
     now
    -0.90
     since
    -0.88
     those
    -0.87
     欣赏
    -0.87
     any
    -0.85
     this
    -0.82
     its
    -0.81
     for
    -0.81
     there
    -0.81
    POSITIVE LOGITS
     enlar
    0.99
    ît
    0.97
    zzlement
    0.96
     opium
    0.94
     innumer
    0.93
     AES
    0.92
     précédents
    0.91
     blessure
    0.90
     coarsely
    0.89
     instr
    0.88
    Activations Density 0.000%

    No Known Activations