© 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. 54046
    Prev
    Next
    INDEX
    Explanations

    consistent

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

    The neuron fires on occurrences of the adjective “consistent,” i.e. mentions of consistency or steadiness.

    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
     condividere
    -1.11
     üblichen
    -1.10
     secretario
    -1.09
    ruzione
    -1.08
     ambitions
    -1.02
    SEGU
    -1.02
    etzten
    -1.02
    𝒥
    -1.01
     पूरी
    -1.01
     conseillers
    -1.00
    POSITIVE LOGITS
     throughout
    1.60
     across
    1.24
     high
    1.18
    Throughout
    1.14
     delivery
    1.06
     stream
    1.05
     year
    1.05
     consistently
    1.03
     output
    1.02
     pattern
    1.02
    Activations Density 0.048%

    No Known Activations