© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8491
    Prev
    Next
    INDEX
    Explanations

    appropriate followed by noun

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

    The neuron consistently fires on occurrences of the word “appropriate.”

    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
    蹰
    -2.88
    archiwizowane
    -2.75
     avec
    -2.72
     με
    -2.72
    }$
    -2.70
    ⎚
    -2.70
    ebab
    -2.69
    􏿿
    -2.67
    derdag
    -2.66
    ╽
    -2.58
    POSITIVE LOGITS
    鋮
    3.28
    焌
    2.95
    ஂ
    2.80
    酲
    2.80
    浥
    2.69
    ”،
    2.64
    ･･
    2.59
    Ⲉ
    2.56
    
    2.53
    翾
    2.53
    Activations Density 0.008%

    No Known Activations