© 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. 112700
    Prev
    Next
    INDEX
    Explanations

    loss of

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

    The neuron activates on numeric measurements and quantities (e.g. “decreased 23.5”), i.e. numbers 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
     oorsp
    -2.20
    Архівовано
    -2.13
    靺
    -2.05
    kipun
    -2.00
    出來的
    -1.99
    ໋
    -1.93
    莼
    -1.90
     parlement
    -1.90
     compositeur
    -1.88
    麽
    -1.86
    POSITIVE LOGITS
    ’
    3.64
    }
    2.50
    it
    2.20
    a
    2.06
     who
    2.05
    ↵
    2.05
    "
    2.05
    焄
    2.05
    '
    2.00
     which
    1.91
    Activations Density 0.005%

    No Known Activations