© 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. 22-GEMMASCOPE-RES-131K
    7. 15063
    Prev
    Next
    INDEX
    Explanations

    dates, times, and statistics

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

    The neuron fires on numeric tokens containing decimal points (i.e. fractional numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     VID
    -1.27
     taget
    -1.24
    ”،
    -1.24
     Grüßen
    -1.23
     -->>
    -1.22
     ©️
    -1.20
    😭
    -1.20
    🎶
    -1.17
    ISCHE
    -1.16
     ▼
    -1.16
    POSITIVE LOGITS
     can
    1.18
    escuela
    1.15
    ところに
    1.13
     Erwachsene
    1.12
    感じです
    1.11
    真的好
    1.09
    感じが
    1.09
    感じで
    1.09
    NewLabel
    1.09
     blijven
    1.06
    Activations Density 0.131%

    No Known Activations