© 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. 111983
    Prev
    Next
    INDEX
    Explanations

    coming soon, announced, determined, change

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

    The neuron detects words and phrases that signal something forthcoming, tentative, or subject to change (e.g., “coming,” “soon,” “to be built,” “subject to change”).

    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
     are
    -1.90
     случайно
    -1.61
     MOST
    -1.59
     müm
    -1.52
    好きです
    -1.50
     através
    -1.48
     ponen
    -1.48
     hacen
    -1.48
     dará
    -1.44
     hará
    -1.42
    POSITIVE LOGITS
    </strong>
    1.63
     县
    1.59
     放題
    1.48
    ⦆
    1.44
    ја
    1.42
    Александр
    1.41
    ઁ
    1.40
    īgs
    1.38
     Alemanha
    1.38
    كتور
    1.38
    Activations Density 0.008%

    No Known Activations