© 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. 10-GEMMASCOPE-RES-131K
    7. 101752
    Prev
    Next
    INDEX
    Explanations

    be one of

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

    The neuron fires on verbs (various conjugated or infinitive forms across languages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    With
    -3.47
    When
    -3.45
    Since
    -3.25
    From
    -3.22
    Having
    -3.17
    This
    -3.14
    Because
    -3.13
    While
    -2.97
    Are
    -2.95
    Just
    -2.94
    POSITIVE LOGITS
     a
    2.45
    
    2.34
     facilita
    2.22
    噲
    2.22
     spearheaded
    2.20
     reconocida
    2.14
    立马
    2.05
    ⸫
    2.05
    indicated
    2.05
    ឵
    2.03
    Activations Density 0.001%

    No Known Activations