© 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. 34654
    Prev
    Next
    INDEX
    Explanations

    attributes and properties or states

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

    This neuron detects tokens that start a new line (i.e. the first word or symbol at the beginning of a line or paragraph).

    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
     corriger
    -1.11
     MODERN
    -1.08
     praktik
    -1.05
    
    -1.05
     faciliter
    -1.04
     substan
    -1.02
    chall
    -1.02
     subtil
    -1.01
    Abuse
    -1.01
    Gün
    -1.00
    POSITIVE LOGITS
     goals
    1.40
     conditions
    1.29
     facts
    1.28
     goal
    1.25
     actions
    1.20
     action
    1.19
     attributes
    1.17
     effects
    1.14
     properties
    1.13
     objects
    1.13
    Activations Density 0.011%

    No Known Activations