© 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. 34574
    Prev
    Next
    INDEX
    Explanations

    transmitter unit

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

    The neuron is looking for numeric literals (numbers) in structured or code-like 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
    Rptr
    -1.07
    Thus
    -1.01
     everything
    -1.00
    だいぶ
    -0.99
     Käufer
    -0.97
     conductores
    -0.95
     Schluß
    -0.94
    Dış
    -0.92
    NameExpr
    -0.92
     drei
    -0.91
    POSITIVE LOGITS
    を
    1.06
    という
    1.03
     with
    0.98
     inquisitive
    0.97
    これは
    0.96
    󠁣
    0.91
    が
    0.90
    岁的
    0.87
    ร์
    0.87
    湾
    0.87
    Activations Density 0.005%

    No Known Activations