© 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. 68795
    Prev
    Next
    INDEX
    Explanations

    events and actions

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

    The neuron primarily fires on action‐denoting verbs.

    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
    <bos>
    -1.34
    These
    -1.01
    There
    -1.01
     profile
    -1.00
    ..!!
    -0.98
    i
    -0.97
    The
    -0.96
    Both
    -0.96
    に対する
    -0.94
     theses
    -0.94
    POSITIVE LOGITS
     estadounid
    1.40
    isic
    1.17
    esseur
    1.17
    さあ
    1.15
    
    1.13
    さぁ
    1.12
    /
    1.12
    aneity
    1.11
    鼉
    1.11
    
    1.09
    Activations Density 0.071%

    No Known Activations