© 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. 100377
    Prev
    Next
    INDEX
    Explanations

    this one is

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

    This neuron detects evaluative opinion phrases of the form “is [adverb] [adjective]” (e.g. “is pretty impressive,” “is truly interesting,” “is well worth a look”).

    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
    0
    -2.05
     these
    -1.66
    2
    -1.62
    鉿
    -1.50
    这
    -1.42
    
    -1.40
    嗵
    -1.40
    这些
    -1.35
    一个
    -1.35
    4
    -1.34
    POSITIVE LOGITS
    StoryboardSegue
    1.88
    служба
    1.51
    ypress
    1.51
    饽
    1.48
    rints
    1.48
    旆
    1.47
    倏
    1.45
     丝
    1.44
    LayoutStyle
    1.43
    vedra
    1.40
    Activations Density 0.016%

    No Known Activations