© 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. 73157
    Prev
    Next
    INDEX
    Explanations

    effects on or against

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

    The neuron is specifically attuned to quantitative and measurement‐style terms—numbers, decimals, percentages, and words like “effects,” “exposure,” or “fault” that typically accompany reported experimental or statistical results.

    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
     this
    -2.05
    )
    -1.81
     not
    -1.68
     these
    -1.66
     started
    -1.52
     people
    -1.36
     only
    -1.35
     helped
    -1.32
     a
    -1.31
     just
    -1.30
    POSITIVE LOGITS
    蔸
    1.52
    Either
    1.43
    鋦
    1.34
    穿过
    1.34
     PERFECT
    1.32
     maî
    1.32
     zoude
    1.32
    色々と
    1.31
    Furthermore
    1.30
     étend
    1.30
    Activations Density 0.354%

    No Known Activations