© 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. 118873
    Prev
    Next
    INDEX
    Explanations

    approximate

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

    The neuron fires on occurrences of the word “approximate,” detecting when the text uses that term to signal approximation.

    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
    秾
    -3.11
    ra
    -2.86
    see
    -2.67
    ☆☆☆☆
    -2.66
    }$
    -2.56
    derdag
    -2.53
    栳
    -2.45
    ため
    -2.42
    的
    -2.41
    ᵴ
    -2.38
    POSITIVE LOGITS
    ↵
    3.25
     Hinblick
    3.02
    ･･
    2.77
    酲
    2.72
    Примеча
    2.66
    尛
    2.66
    了一种
    2.58
    d
    2.56
    犊
    2.53
    釆
    2.48
    Activations Density 0.005%

    No Known Activations