© 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. 104336
    Prev
    Next
    INDEX
    Explanations

    bump

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

    The neuron detects occurrences of the substring “bump” (including its inflected or compound forms).

    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
    ']
    -2.81
     }
    -2.67
    as
    -2.58
    for
    -2.53
    _
    -2.34
     None
    -2.33
     It
    -2.31
     剤
    -2.27
    как
    -2.27
                
    -2.27
    POSITIVE LOGITS
    ⬮
    3.69
    ſſi
    2.81
    赑
    2.63
    ೢ
    2.58
     奶
    2.58
    嫒
    2.55
    
    2.52
    虓
    2.50
    来自于
    2.48
    Ꮸ
    2.48
    Activations Density 0.003%

    No Known Activations