© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129664
    Prev
    Next
    INDEX
    Explanations

    at the time

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

    The neuron activates on numeric expressions with decimal points (e.g., percentages or precise measurements).

    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
     tomorrow
    -1.29
    gelopen
    -1.27
    ኽ
    -1.20
     新款
    -1.19
    рович
    -1.19
    digkeit
    -1.19
     ANIMALS
    -1.18
    ⢮
    -1.18
     жовтня
    -1.18
     since
    -1.18
    POSITIVE LOGITS
    /
    1.69
    >
    1.38
    og
    1.25
    8
    1.24
    -
    1.23
    9
    1.20
     здание
    1.17
    他就
    1.16
    »,
    1.16
    他不
    1.16
    Activations Density 0.017%

    No Known Activations