© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65254
    Prev
    Next
    INDEX
    Explanations

    arranging instant money

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

    The neuron fires on words that indicate arranging or planning actions (e.g., “plan,” “schedule,” “arrange,” “organizing”).

    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
     tandis
    -1.25
    Despite
    -1.24
     mantener
    -1.23
     έχουν
    -1.23
     zamiast
    -1.21
     lograr
    -1.19
     spodnie
    -1.19
     gelegt
    -1.18
    }")]
    -1.16
     dividida
    -1.15
    POSITIVE LOGITS
     for
    2.69
     to
    1.48
    であれば
    1.47
     with
    1.40
     she
    1.29
    omorphisms
    1.28
    を使って
    1.24
    iffance
    1.24
     if
    1.23
     для
    1.22
    Activations Density 0.075%

    No Known Activations