© 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. 10-GEMMASCOPE-RES-131K
    4. 105699
    Prev
    Next
    INDEX
    Explanations

    cucumber and pickles

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

    mentions of cucumber or cucumbers in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on mentions of “cucumber” (and related cucurbit terms) in the text.

    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
    		
    -2.88
    at
    -2.67
    訁
    -2.63
    也是
    -2.48
    也有
    -2.27
    需要
    -2.25
    在
    -2.14
    ,;
    -2.09
    这个
    -2.02
     aquella
    -2.02
    POSITIVE LOGITS
     When
    2.17
    另一种
    2.02
     детям
    1.86
    																		
    1.84
    乓
    1.83
    了过来
    1.82
     considérons
    1.82
     delicada
    1.79
    子を
    1.76
    后期
    1.74
    Activations Density 0.005%

    No Known Activations