© 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. 22-GEMMASCOPE-RES-131K
    7. 36719
    Prev
    Next
    INDEX
    Explanations

    names and entities

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

    The neuron fires on capitalized tokens marking proper names and places.

    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
     when
    -1.03
     buen
    -0.98
    
    -0.95
    €“
    -0.92
     excellente
    -0.87
    ర్
    -0.84
     světě
    -0.84
    工程师
    -0.83
     estoppel
    -0.82
    。
    -0.82
    POSITIVE LOGITS
     hierfür
    1.10
    他想
    1.05
     grijs
    1.01
     geox
    1.01
     venezia
    0.98
     sembler
    0.98
     trusty
    0.96
    逦
    0.96
     magnético
    0.96
    hite
    0.96
    Activations Density 0.086%

    No Known Activations