© 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. 58789
    Prev
    Next
    INDEX
    Explanations

    cost and surrounding words

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

    The neuron specifically detects occurrences of the word “Cost” (often capitalized) 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
    vantaged
    -3.45
    öpfer
    -3.39
    "
    -3.30
    CHREIB
    -2.98
    薷
    -2.83
    愎
    -2.81
    蹋
    -2.72
    茈
    -2.69
     enactment
    -2.52
    蟜
    -2.52
    POSITIVE LOGITS
    ing
    5.13
    o
    3.81
    u
    3.58
    er
    3.34
    y
    3.30
    ة
    3.19
    ed
    3.09
    an
    3.08
    ে
    2.94
    𐌺
    2.91
    Activations Density 0.006%

    No Known Activations