© 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. 9879
    Prev
    Next
    INDEX
    Explanations

    flooding

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

    The neuron fires on occurrences of flood‐related terms (in particular the word “flooding”).

    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
    en
    -2.61
    er
    -2.44
    ний
    -2.23
    “
    -2.22
    ↵↵
    -2.20
     возможности
    -2.13
    และ
    -2.08
    blurRadius
    -2.08
    A
    -2.05
    薷
    -2.05
    POSITIVE LOGITS
    ."
    2.83
    鸶
    2.75
    垕
    2.72
    ;
    2.64
    鈇
    2.63
    蚡
    2.56
    ↵
    2.44
     partic
    2.28
    我跟
    2.19
    淠
    2.19
    Activations Density 0.002%

    No Known Activations